Entries |
Document | Title | Date |
20080201282 | System and Method for Locating Points of Interest in an Object Image Implementing a Neural Network - A system is provided for locating at least two points of interest in an object image. One such system uses an artificial neural network and has a layered architecture having: an input layer, which receives the object image; at least one intermediate layer, known as the first intermediate layer, consisting of a plurality of neurons that can be used to generate at least two saliency maps, which are each associated with a different pre-defined point of interest in the object image; and at least one output layer, which contains the aforementioned saliency maps. The maps include a plurality of neurons, which are each connected to all of the neurons in the first intermediate layer. The points of interest are located in the object image by the position of a unique global maximum on each of the saliency maps. | 08-21-2008 |
20080208781 | REDUCTION OF CLASSIFICATION ERROR RATES AND MONITORING SYSTEM USING AN ARTIFICIAL CLASS - Systems and methods for enhancing the accuracy of classifying a measurement by providing an artificial class. Seizure prediction systems may employ a classification system including an artificial class and a user interface for signaling uncertainty in classification when a measurement is classified in the artificial class. | 08-28-2008 |
20080215514 | Portable device for classification of medical data - A portable device for classification of medical data, the portable device having an artificial neural network and a configuration store having configuration parameter information relating to the artificial neural network, the artificial neural network being configured in accordance with configuration parameter information, the portable device being operable to receive input data, pass the input data to the ANN, and receive an output from the ANN. | 09-04-2008 |
20080228678 | REAL TIME BACKUP SYSTEM FOR COMPUTER USERS - This invention involves tracking and backing all the information that a user generates on its computer devices (including embedded devices) in real time. The local user server records all user actions and gestures (via various means that include TV cameras). All of this information (user actions and saved files in a computer) is then sent to a remote server via the Internet. This remote server has a virtual map of all the embedded devices on a computer that the person uses. The remote server immediately starts to interpret the user's actions (including user gestures). In one implementation, the invention stores user actions that are related to data generation (e.g. actions that called some links where data is stored, or executed some programs that generated data). In another variant the remote server generates and downloads the same files that are downloaded on the local user computer devices. For example, if a person begins to download a program, the server may also download the same program on a remote backup server. This way, if the user loses this program, it can be retrieved automatically through a provided server on the Internet. If user's files are backed up by regular backup periodically, relevant data that were stored by real time backup servers can be eliminated. | 09-18-2008 |
20080235170 | USING SCENARIO-RELATED METADATA TO DIRECT ADVERTISING - Mechanisms for directing advertising in search result presentation and/or scenario solution execution based upon a user's locality are provided. Locality refers to a collection of metadata created based upon scenario solutions executed by a user and/or enablers acquired by a user during scenario solution execution. For instance, embodiments of the present invention provide a mechanism by which scenario solutions or enablers related to commonly executed scenario solutions or enablers stored in association with the user's locality can be advertised to the user in conjunction with presentation of scenario solution-related search results. Additionally, embodiments of the present invention provide a mechanism by which more highly rated scenario solutions and/or enablers than those associated with the user's locality may be advertised during presentation of an executed scenario solution. | 09-25-2008 |
20080256007 | Learning A* priority function from unlabeled data - A technique for increasing efficiency of inference of structure variables (e.g., an inference problem) using a priority-driven algorithm rather than conventional dynamic programming. The technique employs a probable approximate underestimate which can be used to compute a probable approximate solution to the inference problem when used as a priority function (“a probable approximate underestimate function”) for a more computationally complex classification function. The probable approximate underestimate function can have a functional form of a simpler, easier to decode model. The model can be learned from unlabeled data by solving a linear/quadratic optimization problem. The priority function can be computed quickly, and can result in solutions that are substantially optimal. Using the priority function, computation efficiency of a classification function (e.g., discriminative classifier) can be increased using a generalization of the A* algorithm. | 10-16-2008 |
20080256008 | Human Artificial Intelligence Machine - A method of creating human artificial intelligence in machines and computer software is presented here, as well as methods to simulate human reasoning, thought and behavior. The present invention serves as a universal artificial intelligence program that will store, retrieve, analyze, assimilate, predict the future and modify information in a manner and fashion which is similar to human beings and which will provide users with a software application that will serve as the main intelligence of one or a multitude of computer based programs, software applications, machines or compilation of machinery. | 10-16-2008 |
20080262990 | SYSTEMS AND METHODS FOR PROCESSING DATA FLOWS - A flow processing facility, which uses a set of artificial neurons for pattern recognition, such as a self-organizing map, in order to provide security and protection to a computer or computer system supports unified threat management based at least in part on patterns relevant to a variety of types of threats that relate to computer systems, including computer networks. Flow processing for switching, security, and other network applications, including a facility that processes a data flow to address patterns relevant to a variety of conditions are directed at internal network security, virtualization, and web connection security. A flow processing facility for inspecting payloads of network traffic packets detects security threats and intrusions across accessible layers of the IP-stack by applying content matching and behavioral anomaly detection techniques based on regular expression matching and self-organizing maps. Exposing threats and intrusions within packet payload at or near real-time rates enhances network security from both external and internal sources while ensuring security policy is rigorously applied to data and system resources. Intrusion Detection and Protection (IDP) is provided by a flow processing facility that processes a data flow to address patterns relevant to a variety of types of network and data integrity threats that relate to computer systems, including computer networks. | 10-23-2008 |
20080262991 | SYSTEMS AND METHODS FOR PROCESSING DATA FLOWS - A flow processing facility, which uses a set of artificial neurons for pattern recognition, such as a self-organizing map, in order to provide security and protection to a computer or computer system supports unified threat management based at least in part on patterns relevant to a variety of types of threats that relate to computer systems, including computer networks. Flow processing for switching, security, and other network applications, including a facility that processes a data flow to address patterns relevant to a variety of conditions are directed at internal network security, virtualization, and web connection security. A flow processing facility for inspecting payloads of network traffic packets detects security threats and intrusions across accessible layers of the IP-stack by applying content matching and behavioral anomaly detection techniques based on regular expression matching and self-organizing maps. Exposing threats and intrusions within packet payload at or near real-time rates enhances network security from both external and internal sources while ensuring security policy is rigorously applied to data and system resources. Intrusion Detection and Protection (IDP) is provided by a flow processing facility that processes a data flow to address patterns relevant to a variety of types of network and data integrity threats that relate to computer systems, including computer networks. | 10-23-2008 |
20080270334 | CLASSIFYING FUNCTIONS OF WEB BLOCKS BASED ON LINGUISTIC FEATURES - A classification system trains a classifier to classify blocks of the web page into various classifications of the function of the block. The classification system trains a classifier using training web pages. To train a classifier, the classification system identifies the blocks of the training web pages, generates feature vectors for the blocks that include a linguistic feature, and inputs classification labels for each block. The classification system learns the coefficients of the classifier using any of a variety of machine learning techniques. The classification system can then use the classifier to classify blocks of web pages. | 10-30-2008 |
20080270335 | PULSE SIGNAL CIRCUIT, PARALLEL PROCESSING CIRCUIT, AND PATTERN RECOGNITION SYSTEM - A pulse signal processing circuit, a parallel processing circuit, and a pattern recognition system including a plurality of arithmetic elements for outputting pulse signals and at least one modulation circuit, synaptic connection element(s), or synaptic connection means for modulating the pulse signals, the modulated pulse signals then being separately or exclusively output to corresponding signal lines. | 10-30-2008 |
20080319932 | CLASSIFICATION USING A CASCADE APPROACH - A system and method that facilitates and effectuates optimizing a classifier for greater performance in a specific region of classification that is of interest, such as a low false positive rate or a low false negative rate. A two-stage classification model can be trained and employed, where the first stage classification is optimized over the entire classification region and the second stage classifier is optimized for the specific region of interest. During training the entire set of training data is employed by a first stage classifier. Only data that is classified by the first stage classifier or by cross validation to fall within a region of interest is used to train the second stage classifier. During classification, data that is classified within the region of interest by the first classification is given the first stage classifier's classification value, otherwise the classification value for the instance of data from the second stage classifier is used. | 12-25-2008 |
20090006292 | RECOGNIZING INPUT GESTURES - The present invention extends to methods, systems, and computer program products for recognizing input gestures. A neural network is trained using example inputs and backpropagation to recognize specified input patterns. Input gesture data is representative of movements in contact on a multi-touch input display surface relative to one or more axes over time. Example inputs used for training the neural network to recognize a specified input pattern can be created from sampling input gesture data for example input gestures known to represent the specified input pattern. Trained neural networks can subsequently be used to recognize input gestures that are similar to known input gestures as the specified input pattern corresponding to the known input gestures. | 01-01-2009 |
20090006293 | METHODS AND SYSTEMS FOR SCALABLE HIERARCHICAL FEED-FORWARD PROCESSES - Methods and systems for constructing a scalable feed-forward process are provided. The method includes identifying a plurality of segments of the process wherein the segments define a feed-forward network which is used to constrain the creation of more detailed segment components. The method also includes modeling each component by defining component outputs and determining component inputs that are combinable using the model to produce the defined output, ordering the components hierarchically based on the respective component outputs and inputs, determining segment inputs and outputs based on the component outputs and inputs, and ordering the segments hierarchically based on the respective segment outputs and inputs. | 01-01-2009 |
20090018985 | HISTOGRAM-BASED CLASSIFIERS HAVING VARIABLE BIN SIZES - A “Classifier Trainer” trains a combination classifier for detecting specific objects in signals (e.g., faces in images, words in speech, patterns in signals, etc.). In one embodiment “multiple instance pruning” (MIP) is introduced for training weak classifiers or “features” of the combination classifier. Specifically, a trained combination classifier and associated final threshold for setting false positive/negative operating points are combined with learned intermediate rejection thresholds to construct the combination classifier. Rejection thresholds are learned using a pruning process which ensures that objects detected by the original combination classifier are also detected by the combination classifier, thereby guaranteeing the same detection rate on the training set after pruning. The only parameter required throughout training is a target detection rate for the final cascade system. In additional embodiments, combination classifiers are trained using various combinations of weight trimming, bootstrapping, and a weak classifier termed a “fat stump” classifier. | 01-15-2009 |
20090030860 | MESSAGE ROUTING USING CYCLICAL NEURAL NETWORKS - A system for routing business-to-business (“B2B”) messages includes a cyclical neural network. The cyclical neural network contains neurons for determining a needed destination of a message based on content type of the message, for example. Neurons are monitored to establish a “state of understanding” of the network during processing, and tags may be applied to messages upon a determination of the needed destination. | 01-29-2009 |
20090037353 | Method and system for evaluating tests used in operating system fingerprinting - In a system for evaluating classification systems such as an operating system (OS) fingerprinting tool (e.g., Nmap), information gain is used as a metric to evaluate the quality of the tool's classification tests, including fingerprinting tests and their associated probes. Information gain is determined using the OS fingerprinting tool's signature database rather than raw training samples, including taking into account signatures/data that are represented by ranges of test values, disjunctive values, and missing values. Uniform distributions over test values and classifications are assumed in applying these methods to an example signature database for Nmap. Other assumptions or a priori information (e.g., normal distributions over ranges) can also be accommodated. The information gain measure provided can be applied to other classification problems as well. | 02-05-2009 |
20090043720 | DOMAIN NAME STATISTICAL CLASSIFICATION USING CHARACTER-BASED N-GRAMS - Systems and methods of classifying domain names are disclosed herein. Character-based n-grams are derived from a domain name in order to classify such domain name in one or more pre-established categories. In one aspect, a geometrical approach is used. Domain name character-based n-grams are mapped to vector points in a multidimensional space. In addition, vector points for various other domain names, which belong to a domain name classification, can be mapped multidimensional space. The number of dimensions in the multidimensional space is the number of different n-grams that can exist for an n-character combination. The relationship between the domain name vector point and the vector points of the various other domain names is used as an indicator of the classification of the domain name vector point. In another aspect, the classification system can be configured to utilize statistical methods. Relative frequencies of one or more character-based n-grams in various classifications are used as indicators. For example, a dictionary set of character-based n-grams can be derived from one or more domain names. The character-based n-grams in the dictionary set can be associated with probability indicative to the likelihood that the character-based n-gram is found in a domain name of a given classification. Such probability can serve as an estimator of a classification of a new domain name having such character-based n-gram. | 02-12-2009 |
20090043721 | DOMAIN NAME GEOMETRICAL CLASSIFICATION USING CHARACTER-BASED N-GRAMS - Systems and methods of classifying domain names are disclosed herein. Character-based n-grams are derived from a domain name in order to classify such domain name in one or more pre-established categories. In one aspect, a geometrical approach is used. Domain name character-based n-grams are mapped to vector points in a multidimensional space. In addition, vector points for various other domain names, which belong to a domain name classification, can be mapped multidimensional space. The number of dimensions in the multidimensional space is the number of different n-grams that can exist for an n-character combination. The relationship between the domain name vector point and the vector points of the various other domain names is used as an indicator of the classification of the domain name vector point. In another aspect, the classification system can be configured to utilize statistical methods. Relative frequencies of one or more character-based n-grams in various classifications are used as indicators. For example, a dictionary set of character-based n-grams can be derived from one or more domain names. The character-based n-grams in the dictionary set can be associated with probability indicative to the likelihood that the character-based n-gram is found in a domain name of a given classification. Such probability can serve as an estimator of a classification of a new domain name having such character-based n-gram. | 02-12-2009 |
20090055336 | SYSTEM AND METHOD FOR CLASSIFYING MULTIMEDIA DATA - A system for classifying multimedia data is provided. The system comprises a characteristic extracting unit configured for obtaining the multimedia data from the mobile apparatus, and extracting characteristics of multimedia data by using the MPEG-7; and a neural network model configured for predefining a training model, and classifying the multimedia data by classifying the characteristics according to the predefined training model. A related method is also provided. | 02-26-2009 |
20090063377 | System and method using sampling for allocating web page placements in online publishing of content - An improved system and method is provided for using sampling for allocating web page placements in online publishing of content. A multi-armed bandit engine may be provided for sampling content items by allocating web page placements of varying quality for content items and optimizing the payoff to maximize revenue. Publishers may provide content items to be published and report their valuation per click. Through a process of valuation discovery, the click-through rate for content items and the value of content items may be learned through sampling. As the process of valuation discovery progresses, the present invention may more closely approximate the click-through rates for content items in order to allocate web page placements to content items that may optimize content layout by maximizing revenue. The present invention may accurately learn the CTR for new content items and support multiple web page placements of varying quality. | 03-05-2009 |
20090094177 | METHOD FOR EFFICIENT MACHINE-LEARNING CLASSIFICATION OF MULTIPLE TEXT CATEGORIES - A method, system and computer-readable medium are presented for performing multiple-category classification of digital documents using non-binary classification approach that is less computationally intensive and does not require the generation of extra parameters in execution. The method comprises calculating a category score for categories to which a digital document may be classified. The category score is based on the relevance of the text in document. Threshold scores for each of the categories are determined to define a number of candidate relevance types. A candidate relevance type is determined for each the categories based upon the category scores. One or more of the categories are assigned to the document by applying a multiple-category selection rule to each of the categories. The candidate relevance type is used to determine whether the categories assigned to the digital document need further validation. If one or more of the assigned categories needs further validation, the validation is performed. | 04-09-2009 |
20090094178 | COMPUTER-BASED METHOD AND SYSTEM FOR EFFICIENT CATEGORIZING OF DIGITAL DOCUMENTS - A method, system and computer-readable medium are presented for computer-based supervised classification of digital documents that can exclusively identify an optimal category for the single class model by dividing a calculated score of each category into groups (thresholds can be automatically decided from the knowledge base) and can further predict whether it will be subjected to human examination and whether feedback learning should be performed. | 04-09-2009 |
20090099988 | ACTIVE LEARNING USING A DISCRIMINATIVE CLASSIFIER AND A GENERATIVE MODEL TO DETECT AND/OR PREVENT MALICIOUS BEHAVIOR - A malicious behavior detection/prevention system, such as an intrusion detection system, is provided that uses active learning to classify entries into multiple classes. A single entry can correspond to either the occurrence of one or more events or the non-occurrence of one or more events. During a training phase, entries are automatically classified into one of multiple classes. After classifying the entry, a generated model for the determined class is utilized to determine how well an entry corresponds to the model. Ambiguous classifications along with entries that do not fit the model well for the determined class are selected for labeling by a human analyst The selected entries are presented to a human analyst for labeling. These labels are used to further train the classifier and the models. During an evaluation phase, entries are automatically classified using the trained classifier and a policy associated with determined class is applied. | 04-16-2009 |
20090125466 | Rapidly Maturing Expanded Data Transaction Profiles - A first set of variables is introduced into a data transaction scoring system. The first set of variables having a maturity level less than a second set of variables previously matured on the data transaction scoring system. The maturity level corresponding to an amount of exposure to the data transaction scoring system. The amount of exposure affecting a degree of precision for the data transaction scoring system. The first set of variables are introduced by expanding a data transaction profile for the data transaction scoring system including second set of variables to further include the first set of variables. Initial values are assigned for the first set of variables based on a statistical model. After such an assignment, scoring of data transactions using the expanded data transaction profile prior to maturing the data transaction system using the first set of variables can be initiated. Related apparatus, systems, techniques, and articles are also described. | 05-14-2009 |
20090125467 | Proactive detection of metal whiskers in computer systems - One embodiment of the present invention provides a system that proactively monitors and detects metal whisker growth in a target area within a computer system. During operation, the system collects target electromagnetic interference (EMI) signals using one or more antennas positioned in the vicinity of the target area. Next, the system analyzes the target EMI signals to proactively detect the onset of metal whisker growth in the target area. | 05-14-2009 |
20090138418 | LEARNING CONTROL APPARATUS, LEARNING CONTROL METHOD, AND COMPUTER PROGRAM - A learning control apparatus for an autonomous agent including a functional module having a function of multiple inputs and multiple outputs, the function receiving at least one variable and outputting at least one value, includes an estimating unit for estimating a causal relationship of at least one variable, a grouping unit for grouping at least one variable into a variable group in accordance with the estimated causal relationship, a determining for determining a behavior variable corresponding to each of the variable groups, and a layering unit for layering, in accordance with the variable group and the behavior variable, the function corresponding to each variable group, the function receiving the variable grouped into the variable group and outputting the behavior variable. | 05-28-2009 |
20090138419 | FRACTAL MEMORY AND COMPUTATIONAL METHODS AND SYSTEMS BASED ON NANOTECHNOLOGY - Fractal memory systems and methods include a fractal tree that includes one or more fractal trunks. One or more object circuits are associated with the fractal tree. The object circuit(s) can be configured from a plurality of nanotechnology-based components to provide a scalable distributed computing architecture for fractal computing. Additionally, a plurality of router circuits is associated with the fractal tree, wherein one or more fractal addresses output from a recognition circuit can be provided at a fractal trunk by the router circuits. | 05-28-2009 |
20090144212 | Enhanced Learning and Recognition Operations for Radial Basis Functions - Methods, apparatuses and systems directed to pattern identification and pattern recognition. In some particular implementations, the invention provides a flexible pattern recognition platform including pattern recognition engines that can be dynamically adjusted to implement specific pattern recognition configurations for individual pattern recognition applications. In some implementations, the present invention also provides for a partition configuration where knowledge elements can be grouped and pattern recognition operations can be individually configured and arranged to allow for multilevel pattern recognition schemes. | 06-04-2009 |
20090157578 | SYSTEM AND METHOD FOR GENERATING A CLASSIFIER MODEL - Generally, the present invention provides a method and computerized system for generating a classifier model, wherein the classifier model is operative to classify web content. The method and computerized system includes a first step of defining a plurality of predictive performance measures based on a leave one out (LOO) cross validation in terms of selectable model parameters. Exemplary predictive performance measures includes smoothened predictive measures such as F-measure, weighted error rate measure, area under curve measure, by way of example. The method and computerized system further includes deriving efficient analytical expressions for predictive performance measures to compute the LOO predictive performance and their derivatives. The next step is thereupon selecting a classifier model based on the LOO predictive performance. | 06-18-2009 |
20090171873 | DETERMINING THE INTERESTINGNESS OF CONTENT UPDATE NOTIFICATIONS - A notification server rates the interest a first user has in notifications associated with events generated by a plurality of interactions with an online community. The notification server receives a plurality of notifications for a first user from a plurality of other users indicating an event has occurred in response to the other users' interactions with the online community. Each notification is rated based on the connections between the first user and the user associated with the notification. The connections may indicate a type of relationship between the first user and the user associated with the notification or the connections may indicate the first user's interest in the event associated with the notification. Each notification is rated based on the connections. The rated notifications are displayed to the first user based on their respective ratings. | 07-02-2009 |
20090204558 | METHOD FOR TRAINING A LEARNING MACHINE HAVING A DEEP MULTI-LAYERED NETWORK WITH LABELED AND UNLABELED TRAINING DATA - A method for training a learning machine having a deep network with a plurality of layers, includes applying a regularizer to one or more of the layers of the deep network; training the regularizer with unlabeled data; and training the deep network with labeled data. Also, an apparatus for use in discriminative classification and regression, including an input device for inputting unlabeled and labeled data associated with a phenomenon of interest; a processor; and a memory communicating with the processor. The memory includes instructions executable by the processor for implementing a learning machine having a deep network structure and training the learning machine by applying a regularizer to one or more of the layers of the deep network; training the regularizer with unlabeled data; and training the deep network with labeled data. | 08-13-2009 |
20090210368 | SYSTEM AND METHOD FOR REAL TIME PATTERN IDENTIFICATION - A method for near real time patterns identification, in one example embodiment, comprises receiving a data stream containing information associated with a transaction and participants of the transaction and receiving an Artificial Intelligence (AI) algorithm trained to score data in the data stream. The method may further comprise receiving metadata associated with the historical information, comparing the data stream to the metadata by measuring differences between variables included in the historical metadata and the data stream. The method may further comprise modifying the data stream to suit the AI algorithm when the differences between variables are below predetermined threshold values and retraining the AI algorithm based on the data stream when the differences between the variables are greater than the predetermined threshold values. The method may further comprise feeding the data stream to the AI algorithm to classify the variables in the data stream. | 08-20-2009 |
20090216696 | DETERMINING RELEVANT INFORMATION FOR DOMAINS OF INTEREST - Techniques are described for determining and using relevant information related to domains of interest. In at least some situations, the techniques include automatically analyzing documents, terms and other information related to a domain of interest in order to automatically determine information about relevant themes within the domain and/or about which documents have contents that are relevant to such themes. Such automatically determined information related to a domain may then be used in various ways, including to assist users in specifying themes of interest and/or in obtaining documents and/or document fragments with contents that are relevant to specified themes. In addition, information about how the automatically determined information is used by users may be tracked and used as feedback for learning improved determinations of relevant themes and relevant documents within the domain, such as by using automated machine learning techniques. | 08-27-2009 |
20090240641 | OPTIMIZING METHOD OF LEARNING DATA SET FOR SIGNAL DISCRIMINATION APPARATUS AND SIGNAL DISCRIMINATION APPARATUS CAPABLE OF OPTIMIZING LEARNING DATA SET - A method of the present invention is processed by a selector. The selector selects each member constituting a learning data set from a data set source. Each member of the source is feature data extracted through a transducer and assigned to any one of categories in advance. The selector calculates each member's divergence degree of the source to obtain an average divergence degree. If an output neuron of the output layer of a neural network is related to different categories of all the categories represented by the output layer, the selector includes every member of the source corresponding to the category of the minimum average divergence degree in the selection from the source to the learning data set. The selector also excludes, from the selection, every member of the source corresponding to every remaining category of the different categories. | 09-24-2009 |
20090248599 | UNIVERSAL SYSTEM AND METHOD FOR REPRESENTING AND PREDICTING HUMAN BEHAVIOR - A system and method is disclosed for profiling subjects and objects based on subjects' responses to various objects for purposes of determining and presenting the objects most likely to generate the most positive response from each visitor. Object ratings, such as aesthetic response, preference, interest, or relevancy, are explicitly submitted by subjects or derived implicitly from visitor interactions with the objects. Objects include movies, books, songs, commercial products, news articles, advertisements or any other type of content or physical item. A profiling engine processes the ratings information and generates compact profiles of each subject and object based on the similarities and differences in affinities between the group of subjects and the group of objects. A recommendation engine then generates recommendations to a subject based on similarity between the subject and object profiles. The recommendation engine can also match subjects to other subjects and objects to other objects. The recommendation engine can also predict affinity across object catalogs and across time. Additionally, the object profiles can be clustered to create behavioral object categories. The system has application in personalization, behavioral targeting, Internet retailing and interactive radio, to name but a few applications. | 10-01-2009 |
20090259607 | SYSTEM, METHOD, AND PROGRAM FOR EVALUATING PERFORMANCE OF INTERMOLECULAR INTERACTION PREDICTING APPARATUS - The present invention provides a system, method, and program for evaluating the performance of an intermolecular interaction predicting apparatus. A performance evaluation system evaluates the performance of an intermolecular interaction predicting apparatus using a correlation between structure factors and physicochemical parameters of classification model construction compounds with high and low scores calculated by the intermolecular interaction predicting apparatus. | 10-15-2009 |
20090259608 | Methods and apparatuses for classifying electronic documents - Embodiments of the invention provide methods and apparatuses for classifying electronic documents (e.g., electronic communications) as either spam electronic documents or legitimate electronic documents. In accordance with one embodiment of the invention, each of a plurality of electronic communications is reduced to a corresponding multidimensional vector based on a multi-dimensional vector space. The multi-dimensional vectors represent corresponding electronic documents that have been classified as at least one type of electronic documents. Subsequent electronic documents to be classified are reduced to a corresponding multi-dimensional vector inserted into the multi-dimensional vector space. The electronic documents corresponding to an inserted multi-dimensional vector are classified based upon the proximity of the inserted multi-dimensional vector to at least one previously classified multi-dimensional vectors of the multi-dimensional vector space. | 10-15-2009 |
20090271342 | PERSONALIZED MEDICINE SYSTEM - A method, program storage device and system for developing a Personalized Medicine System ( | 10-29-2009 |
20090276384 | Methods and Devices Relating to Estimating Classifier Performance - Methods and devices, including methods and devices for estimating classifier performance such as generalization performance, are disclosed. One method includes providing multiple samples. Each sample is characterized by one or more features. This method also includes associating a feature variability with at least one of the one or more features on a feature-by-feature basis; and computing a first probability of misclassification by a first classifier using the feature variability. Devices, including integrated circuits (ICs) and field programmable gate arrays (FPGAs), that are configured for use in carrying out the present methods are also disclosed. | 11-05-2009 |
20090287624 | SPATIO-TEMPORAL PATTERN RECOGNITION USING A SPIKING NEURAL NETWORK AND PROCESSING THEREOF ON A PORTABLE AND/OR DISTRIBUTED COMPUTER - A system and method for characterizing a pattern, in which a spiking neural network having at least one layer of neurons is provided. The spiking neural network has a plurality of connected neurons for transmitting signals between the connected neurons. A model for inducing spiking in the neurons is specified. Each neuron is connected to a global regulating unit for transmitting signals between the neuron and the global regulating unit. Each neuron is connected to at least one other neuron for transmitting signals from this neuron to the at least one other neuron, this neuron and the at least one other neuron being on the same layer. Spiking of each neuron is synchronized according to a number of active neurons connected to the neuron. At least one pattern is submitted to the spiking neural network for generating sequences of spikes in the spiking neural network, the sequences of spikes (i) being modulated over time by the synchronization of the spiking and (ii) being regulated by the global regulating unit. The at least one pattern is characterized according to the sequences of spikes generated in the spiking neural network. | 11-19-2009 |
20090307164 | BIOMETRIC SECURITY USING NEUROPLASTIC FIDELITY - A system, method and program product for providing biometric security using neuroplastic fidelity. A method is disclosed that includes: receiving biometric data; analyzing the biometric data with a probabilistic neural network and outputting a chromosome containing a binary string; mapping the binary string to a selected extractor and a selected matcher; apply the selected extractor to the biometric data to generate a template; using the selected matcher to compare the template to a set of stored templates to identify a match; and outputting a result. | 12-10-2009 |
20090313194 | METHODS AND APPARATUS FOR AUTOMATED IMAGE CLASSIFICATION - A system for automated classification of an image of an electronic document such as a facsimile document. The image is converted to a textual representation, and at least some of the terms in the textual representation may be associated with one or more predefined classification types, thereby enabling the document to be classified, and for multi-page documents, determining boundaries used to split the document into sections. The development of associations between terms and classification types may result from providing, to the system, a training set of manually-classified documents. A training module analyzes the training set to calculate probabilities that particular terms may appear in documents of a particular classification type. Probabilities established during training are used during automated document processing to assign a classification type to the document. A confidence score associated with the assigned classification type provides a metric for assessing the accuracy of the automated process. | 12-17-2009 |
20090327181 | BEHAVIOR BASED METHOD AND SYSTEM FOR FILTERING OUT UNFAIR RATINGS FOR TRUST MODELS - Disclosed is a behavior-based method which uses each rater's rating behaviors as the criterion to judge unfair ratings. A behavior refers to the action that a rater gives certain rating under specific context. The behavior-based method regards the rating given by a rater with abnormal behavior as an unfair rating, where abnormal behavior is recognized by comparing a rater's current behavior with his behavior history. | 12-31-2009 |
20100005044 | Remote Detection and Measurement of Objects - Provided are methods of using electromagnetic waves for detecting metal and/or dielectric objects. Methods include directing microwave and/or mm wave radiation in a predetermined direction using a transmission apparatus, including a transmission element; receiving radiation from an entity resulting from the transmitted radiation using a detection apparatus; and generating one or more detection signals in the frequency domain using the detection apparatus. Methods may include operating a controller, wherein operating the controller includes causing the transmitted radiation to be swept over a predetermined range of frequencies, performing a transform operation on the detection signal(s) to generate one or more transformed signals in the time domain, and determining, from one or more features of the transformed signal, one or more dimensions of a metallic or dielectric object upon which the transmitted radiation is incident. | 01-07-2010 |
20100010948 | Learning Device, Learning Method, and Program - A learning device includes: a plurality of learning modules, each of which performs update learning to update a plurality of model parameters of a pattern learning model that learns a pattern using input data; model parameter sharing means for causing two or more learning modules from among the plurality of learning modules to share the model parameters; and sharing strength updating means for updating sharing strengths between the learning modules so as to minimize learning errors when the plurality of model parameters are updated by the update learning. | 01-14-2010 |
20100010949 | Learning Device, Learning Method, and Program - A learning device includes: a plurality of learning modules, each of which performs update learning to update a plurality of model parameters of a pattern learning model that learns a pattern using input data; model parameter sharing means for causing two or more learning modules from among the plurality of learning modules to share the model parameters; and classification means for classifying the plurality of learning modules on the basis of the plurality of model parameters of each of the learning modules after the update learning. | 01-14-2010 |
20100042565 | MEZZAZINE IN-DEPTH DATA ANALYSIS FACILITY - A mezzanine adapter based data processing facility provides in-depth data analysis that is presented as a digest of advanced statistics and network measures including latency data, content analysis, bidirectional flow related characteristics, multiple flow related statistics over a count of connections or over a period of time, and the like. | 02-18-2010 |
20100082510 | TRAINING A SEARCH RESULT RANKER WITH AUTOMATICALLY-GENERATED SAMPLES - A search result ranker may be trained with automatically-generated samples. In an example embodiment, user interests are inferred from user interactions with search results for a particular query so as to determine respective relevance scores associated with respective query-identifier pairs of the search results. Query-identifier-relevance score triplets are formulated from the respective relevance scores associated with the respective query-identifier pairs. The query-identifier-relevance score triplets are submitted as training samples to a search result ranker. The search result ranker is trained as a learning machine with multiple training samples of the query-identifier-relevance score triplets. | 04-01-2010 |
20100094788 | Method for the computer-assisted control and/or regulation of a technical system - A method for the computer-assisted control and/or regulation of a technical system is provided. The method includes two steps, namely learning the dynamics of a technical system using historical data based on a recurrent neuronal network, and the subsequent learning of an optimum regulation by coupling the recurrent neuronal network to another neuronal network. The method can be used with any technical system in order to control the system in an optimum computer-assisted manner. For example, the method can be used in the control of a gas turbine. | 04-15-2010 |
20100100514 | SENSOR UNIT FOR ENVIRONMENT OBSERVATION COMPRISING A NEURAL PROCESSOR - A sensor unit comprising a sensor, a neural processor and a communication device, wherein the sensor unit is adapted to perform pattern recognition by means of the neural processor and to transfer the result of the pattern recognition via the communication device. | 04-22-2010 |
20100121796 | SYSTEM AND METHOD FOR EVALUATING A GAS ENVIRONMENT - A system and method for detecting gas concentrations in a target environment uses an array of sensors. Each sensor generates a respective voltammogram in response to the environment, and the voltammograms are collectively transformed into bins that each have a distribution and a height. Normalized bins are then matched with a training set to determine whether a selected gas is present. Also, an un-normalized bin is fitted with the training set to ascertain a concentration of the gas. For this operation, the training set includes normalized and un-normalized data references previously derived from empirically defined voltammograms. | 05-13-2010 |
20100121797 | STANDOFF DETECTION FOR NITRIC ACID - In one embodiment, a method is disclosed that includes obtaining at least one measurement in a spectral domain of a sample and computing one or more measurements of the salient features in the spectral domain. The salient features correspond to at least one peak within the spectral domain. This method also includes classifying the computed salient features against a feature signature of nitric acid. In addition, this method includes determining if the chemical is present in the sample. | 05-13-2010 |
20100121798 | INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD, PATTERN RECOGNITION APPARATUS, AND PATTERN RECOGNITION METHOD - In a hierarchical neural network having a module structure, learning necessary for detection of a new feature class is executed by a processing module which has not finished learning yet and includes a plurality of neurons which should learn an unlearned feature class and have an undetermined receptor field structure by presenting a predetermined pattern to a data input layer. Thus, a feature class necessary for subject recognition can be learned automatically and efficiently. | 05-13-2010 |
20100153323 | ENSEMBLE METHOD AND APPARATUS FOR CLASSIFYING MATERIALS AND QUANTIFYING THE COMPOSITION OF MIXTURES - A method of and system for generating models with which to classify or quantify spectra of unknown mixtures of compounds to permit the specific identification or quantification of a target analyte in complex mixtures based on spectral data, the method comprising the steps of: providing a training set of training spectra, each spectrum representing a mixture of known compounds and each having a plurality of spectral attributes, each at a different wavelength, choosing a plurality of wavelengths, determining at least the value of the spectral attribute at each chosen wavelength in each training spectrum in the training set, and building a model for each chosen wavelength by correlating the determined attribute values at said chosen wavelength, a method and system for classifying the spectrum of a mixture of unknown compounds, and a method and system for quantifying the spectrum of a mixture of unknown compounds to determine concentrations therein, using said models. | 06-17-2010 |
20100198764 | Methods and Devices Relating to Estimating Classifier Performance - Methods and devices, including methods and devices for estimating classifier performance such as generalization performance, are disclosed. One method includes providing multiple samples. Each sample is characterized by one or more features. This method also includes associating a feature variability with at least one of the one or more features on a feature-by-feature basis; and computing a first probability of misclassification by a first classifier using the feature variability. Devices, including integrated circuits (ICs) and field programmable gate arrays (FPGAs), that are configured for use in carrying out the present methods are also disclosed. | 08-05-2010 |
20100211535 | METHODS AND SYSTEMS FOR MANAGEMENT OF DATA - A method, system and computer program product include a data processing system that comprises a set of data processing modules, the set of data processing modules adapted to assign at least one tag to each data item included in a first set of data items, the first set of data items corresponding to a first application, the first application running on the data processing system. The set of data processing modules are adapted to also assign at least one tag to each data item included in a second set of data items, the second set of data items corresponding to a second application, the second application running on a remote data processing system. The set of data processing modules are further adapted to identify a set of related data items based on corresponding assigned tags, the set of related data items including at least one data item included in the first set of data items and at least one data item included in the second set of data items. | 08-19-2010 |
20100217731 | Computer Implemented Method for the Automatic Classification of Instrumental Citations - The learning method taught in this patent document is significantly different from previous methods for automatic classification of citations that are labor intensive and subject to human bias and error. The present invention automatically generates and avoids these limitations. A set of operational definitions and features uniquely suited to the scientific literature is disclosed along with their use with a learning method that is capable of analyzing the textual content of articles along with bibliometric data to accurately classify instrumental citations. | 08-26-2010 |
20100223218 | DATA PROCESSING APPARATUS AND METHOD FOR AUTOMATICALLY GENERATING A CLASSIFICATION COMPONENT - Data processing apparatus operative ( | 09-02-2010 |
20100241599 | METHOD FOR CLASSIFYING USERS, METHOD AND DEVICE FOR COLLECTING AND ANALYZING BEHAVIORS - A method for classifying users is provided, which includes obtaining user attribute information of a user, matching the user attribute information with pre-determined user groups and/or pre-determined characters, and classifying the user into a user group and/or character that is matched successfully. A device for classifying users, a method for collecting and analyzing behaviors, and a system for collecting and analyzing behaviors are also provided. | 09-23-2010 |
20100280981 | INFORMATION FILTERING SYSTEM, INFORMATION FILTERING METHOD AND INFORMATION FILTERING PROGRAM - A string matching unit | 11-04-2010 |
20100293124 | Method and System for Data Classification in the Presence of a Temporal Non-Stationarity - A method and system for determining a feature of a particular pattern are provided. In particular, data records are received, and predetermined patterns that are associated with at least some of the data records are obtained. Using the system and method, particular information is extracted from at least a subset of the received data records, the particular information being indicative of the particular pattern in at least some of the data records. Then, it is determined whether the particular pattern is an unexpected pattern based on the obtained predetermined patterns. In addition, it is possible to classify and reduce data and/or parameters provided in the data records. First, the data records are received. Then, the data records which have at least one particular pattern are classified using a Multivariate Adaptive Regression Splines technique. Thereafter, the data and/or parameters of the classified data records are shrunk using a Stein's Estimator Rule technique. | 11-18-2010 |
20100299294 | APPARATUS, SYSTEM, AND METHOD FOR DETERMINING A PARTIAL CLASS MEMBERSHIP OF A DATA RECORD IN A CLASS - An apparatus, system, and method are disclosed for determining a partial class membership of a data record in a class. The apparatus includes a record set acquisition module that receives a set of reference records having the same independent variables and belonging to a known class within a group of classes. An unknown-class record receiving module receives an unknown-class record having same independent variables as reference records. A class identification module creates a class vector for each reference record identifying whether the record is in a class. A weighting module calculates a set of unknown-class record weights for the unknown-class record. A classification module determines a partial class membership for the unknown-class record for each class in the group of classes using the set of unknown-class record weights. Each partial class membership identifies a probability that the unknown-class record belongs to a corresponding class in the group of classes. | 11-25-2010 |
20100299295 | MESSAGE ROUTING USING CYCLICAL NEURAL NETWORKS - A system for routing business-to-business (“B2B”) messages includes a cyclical neural network. The cyclical neural network contains neurons for determining a needed destination of a message based on content type of the message, for example. Neurons are monitored to establish a “state of understanding” of the network during processing, and tags may be applied to messages upon a determination of the needed destination. | 11-25-2010 |
20100306144 | SYSTEM AND METHOD FOR CLASSIFYING INFORMATION - An exemplary embodiment of the present invention provides a computer implemented method for classifying information. The method may include accessing a plurality of information sources to identify example information items for each of a plurality of classification categories. Each of the example information items may be analyzed to generate a training corpus for each information source for each of the classification categories. The training corpus for each of the information sources may be combined to generate a training set for each of the classification categories, wherein the training set may be configured to allow the generation of a classification function. | 12-02-2010 |
20100312732 | METHODS AND SYSTEMS FOR RESPONSE DETECTION AND EFFICACY - Techniques are provided for analyzing clinical trial data and other medical information in order to understand heterogeneity of response within a population to a treatment under study. These techniques can support the development of personalized medical treatments and provide a better understanding of variability within the population to the effects of existing and new therapies. Additionally, these techniques can robustly define how subjects in the population respond to a treatment under study to differentiate between different responses, such as non-response and response followed by relapse. Therefore, the likely biology that is different in these responses can be identified to predict future response using any number of identified markers. | 12-09-2010 |
20110016069 | System and method for voice of the customer integration into insightful dimensional clustering - A computer implemented method utilizing Insightful Dimensional Clustering (IDC) to extrapolate characteristics of subscribers that contact customer care to the entire subscriber base is disclosed. The combination of interaction content and IDC results in the spread of rich interaction characteristics to the entire subscriber base resulting in groupings of subscribers with similar characteristics including behavior, preferences, complaints, churn propensities, and pertinent retention offers. | 01-20-2011 |
20110022555 | Computer Algorithm for Automatic Allele Determination from Fluorometer Genotyping Device - The present invention provides methods and systems for an automated method of identifying allele values from data files derived from processed fluorophore emissions detected during the observation of fluorophore labeled nucleotide probes used in analyzing polymorphic DNA are provided. These methods are used in the rapid and efficient distinguishing of targeted polymorphic DNA sites without control samples. | 01-27-2011 |
20110047111 | USE OF NEURAL NETWORKS FOR ANNOTATING SEARCH RESULTS - A system for generating annotations of a document, including a plurality of neurons connected as a neural network, the neurons being associated with words, sentences and documents. An activity regulator regulates a minimum and/or maximum number of neurons of the neural network that are excited at any given time. The neurons are displayed to a user and identify the neurons that correspond to sentences containing a predetermined percentage of document meaning. The annotations can be also based on a context of the user's search query. The query can include keywords, documents considered relevant by the user, or both. Positions of the neurons relative to each other can be changed on a display device, based on input from the user, with the change in position of one neuron changing the resulting annotations. The input from the user can also include changing a relevance of neurons relative to each other, or indicating relevance or irrelevance of a document or sentence. | 02-24-2011 |
20110047112 | Method for Detecting Airplane Flight Events, Mobile Communication Device, and Computational Unit Therefor - A method for detecting airplane flight events using at least one acceleration sensor associated with a mobile communication device includes obtaining at least one acceleration signal from the at least one acceleration sensor; pre-processing the obtained at least one acceleration signal to remove redundant information present in the at least one acceleration signal; performing a feature extraction on the pre-processed at least one acceleration signal; and classifying airplane flight events based on an acceleration pattern represented by the extracted acceleration features. | 02-24-2011 |
20110082824 | Method for selecting an optimal classification protocol for classifying one or more targets - A framework for comparison and optimization of classifiers and features for classification of targets includes preparing training and testing sets, applying a classifier to the training set to achieve a distinctly trained classifier for each classifier applied, applying each resulting trained classifier to the testing data set, selecting an optimal classifier, and applying the optimal classifier to the target. The framework is used to optimally classify a physical representation of a target, such as a document, news article, or advertisement. The framework allows for targeted advertisements to be directed to consumers based on user preferences learned from user activities across a network. | 04-07-2011 |
20110099137 | GRAPHICAL USER INTERFACE COMPONENT CLASSIFICATION - Systems, methods, and other embodiments associated with graphical user interface (GUI) component classification are described. One example method includes generating a first vector. The first vector may be generated based on image data describing a GUI component. The example method may also include assigning a GUI component classifier to the GUI component. Assigning the GUI component classifier may comprise comparing the first vector to members of a vector set. Members of the vector set may describe GUI elements. The example method may also include providing the GUI component classifier. | 04-28-2011 |
20110106739 | METHOD FOR DETERMINING THE PRESENCE OF DISEASE - The invention provides a method for determining presence of a disease, comprising steps of; measuring the levels of expression of transcription products of genes in a biological sample obtained from a subject suspected of having a target disease, wherein the genes comprise at least one gene belonging to each of at least two disease-determining gene families related to the target disease; obtaining values representing deviations by standardizing the levels of the expression based on the levels of expression of transcription products of the corresponding genes in a plurality of healthy subjects; obtaining the average of values representing deviations with respect to the gene belonging to each of the disease-determining gene families; and determining whether or not the subject has the target disease by using the average; as well as a computer program product for determining presence of a disease. | 05-05-2011 |
20110106740 | TISSUE CLASSIFICATION METHOD FOR DIAGNOSIS AND TREATMENT OF TUMORS - The present invention discloses an informational computation method for classifying objects Specifically, the invention is a system, method, and computer-readable media for classifying tumors using a nonparametric statistical classifier in conjunction with an artificial neural network. The invention classifies unknown tumor types based on the correlation of unknown tumor's genetic expression compared to the genetic expression of know tumor types by first performing a nonparametric statistical analysis on the know data, training a artificial neural network with the known data, and then inputting the unknown tumor data into the neural network to calculate the probability that the sample tumor is a member of a class of tumors. By using a statistical classifier in conjunction with a neural network, the invention classifies unknown tumors more accurately then conventionally possible. Advantageously, by using a variety of tumor genetic expression data sets, including both published data sets and generated data sets, a tumor classifier, robust and accurate enough for clinical application, is provided. | 05-05-2011 |
20110112999 | METHOD FOR PREDICTING AND WARNING OF WAFER ACCEPTANCE TEST VALUE - A method for predicting and warning of WAT value includes the steps as follows. A key process is selected and a WAT value after finishing the key process is used as a predictive goal. A predicting model is built. One batch or plural batches of predictive wafers are prepared, and a Fault Detection and Classification data (FDC data) and a metrology data from the predictive wafers of the key process are collected. The FDC data and the metrology data collected from the predictive wafers are inputted into the predicting model for processing a normal predicting procedure, and a predictive WAT value by the predicting model is outputted. The present invention can accurately predict the WAT value, effectively monitor some specific defective wafers and continuously perform the improvement for the specific defective wafer. | 05-12-2011 |
20110125686 | Method for identifying Hammerstein models - The computerized method for identifying Hammerstein models is a method in which the linear dynamic part is modeled by a space-state model and the static nonlinear part is modeled using a radial basis function neural network (RBFNN). Accurate identification of a Hammerstein model requires that output error between the actual and estimated systems be minimized. Thus, the problem of identification is an optimization problem. A hybrid algorithm, based on least mean square (LMS) principles and the Subspace Identification Method (SIM) is developed for the identification of the Hammerstein model. LMS is a gradient-based optimization algorithm that searches for optimal solutions in the negative direction of the gradient of a cost index. In the method, LMS is used for estimating the parameters of the RBFNN. For estimation of state-space matrices, the N4SID algorithm for subspace identification is used. | 05-26-2011 |
20110137840 | COMPREHENSIVE IDENTITY PROTECTION SYSTEM - A system and method for protecting identity fraud are disclosed. A system includes a detection subsystem to identify applications and/or accounts at risk of identity fraud, and a disposition subsystem to process data provided by the detection system and to determine whether identity fraud exists in the applications and/or accounts. According to an implementation, one or more neural network models are defined, each neural network model being configured to handle a class of cases related to the subject and a specific data configuration describing a case of the class. The one or more neural network models are run to generate data requests about the subject's identity, and the data requests are passed to a detection system that monitor transactions associated with the subject. Additional data associated with the transactions is requested until a threshold certainty is achieved or until available data or models are exhausted. | 06-09-2011 |
20110137841 | SAMPLE CLASS PREDICTION METHOD, PREDICTION PROGRAM, AND PREDICTION APPARATUS - To predict the class of an unknown sample, a) a discriminant function for assigning each training sample to class 1 or class 2 is obtained, b) the discriminant score of each training sample and an unknown sample are calculated using the function, c) it is determined whether the score of the unknown sample is either not smaller than the largest score or not larger than the smallest score taken among all of the training samples, d) if the determination in c) is affirmative, the class of the unknown sample is determined based on the score of the unknown sample, e) if the determination in c) is negative, then the training samples having the largest score and the smallest score are removed to form a new training sample set from remaining training samples, and f) a) to e) are repeated. | 06-09-2011 |
20110178967 | METHODS AND APPARATUS FOR DATA ANALYSIS - A method and apparatus for data analysis according to various aspects of the present invention is configured to test a set of components and generate test data for the components. A diagnostic system automatically analyzes the test data to identify a characteristic of a component fabrication process by recognizing a pattern in the test data and classifying the pattern using a neural network. | 07-21-2011 |
20110178968 | SYSTEM AND METHOD FOR DETECTING RESPIRATORY INSUFFICIENCY IN THE BREATHING OF A SUBJECT - Respiratory insufficiency is detected by classifying preliminary breaths identified through a capnogram as being valid or artifact. Individual breaths are classified as being valid or artifact by determining values of a plurality of breathing parameters for a given breath, inferring a value for a key parameter from the determined values for the plurality of breathing parameters, and comparing the inferred value for the key parameter to a predetermined threshold. | 07-21-2011 |
20110225112 | Multifunctional Neural Network System and Uses Thereof - A multifunctional neural network system for prediction which includes memory components to store previous values of data within a network. The memory components provide the system with the ability to learn relationships/patterns existent in the data over time. | 09-15-2011 |
20110246403 | Method and System for Automated Supervised Data Analysis - The invention relates to a method for automatically analyzing data and constructing data classification models based on the data. In an embodiment of the method, the method includes selecting a best combination of methods from a plurality of classification, predictor selection, and data preparatory methods; and determining a best model that corresponds to one or more best parameters of the classification, predictor selection, and data preparatory methods for the data to be analyzed. The method also includes estimating the performance of the best model using new data that was not used in selecting the best combination of methods or in determining the best model; and returning a small set of predictors sufficient for the classification task. | 10-06-2011 |
20110251985 | Detection and Prediction of Physiological Events in People with Sleep Disordered Breathing Using a LAMSTAR Neural Network - Apparatus and methods are disclosed for generating and outputting physiological event results from physiological data related to a patient. Physiological event results include results predicting and/or detecting individual physiological events related to a medical condition of the patient. | 10-13-2011 |
20110270788 | Neural Network For Clustering Input Data Based On A Gaussian Mixture Model - Disclosed are systems, apparatuses, and methods for clustering data. Such a method includes providing input data to each of a plurality of cluster microcircuits of a neural network, wherein each cluster microcircuit includes a mean neural group and a variance neural group. The method also includes determining a response of each cluster microcircuit with respect to the input data. The method further includes modulating the mean neural group and the variance neural group of each cluster microcircuit responsive to a value system. | 11-03-2011 |
20110282816 | LINK SPAM DETECTION USING SMOOTH CLASSIFICATION FUNCTION - A spam detection system is disclosed. The system includes a classifier training component that receives a first set of training pages labeled as normal pages and a second set of training pages labeled as spam pages. The training component trains a web page classifier based on both the first set of training pages and the second set of training pages. A spam detector then receives unlabeled web pages uses the web page classifier to classify the unlabeled web pages as spam pages or normal pages. | 11-17-2011 |
20110289033 | Supervised Learning with Multi-Scale Time Intervals Using a Statistical Classification Model to Classify Unlabeled Events - A method, a system and a computer program product generate a statistical classification model used by a computer system to determine a class associated with an unlabeled time series event. | 11-24-2011 |
20110313962 | METHOD FOR IDENTIFYING EMERGING ISSUES FROM TEXTUAL CUSTOMER FEEDBACK - Systems, methods and software products identify emerging issues from textual customer feedback. A message stream of customer feedback is received. The message stream includes a plurality of unstructured text messages from at least one homogeneous source. A time interval is established. The volume of text messages for the time interval is determined to establish a reference volume. The volume of text messages in subsequent time intervals is measured to establish a trend volume. The trend volume is compared to the reference volume to determine a volumetric change. At least one action is initiated in response to a volumetric change above a pre-determined threshold. At least one action is initiated in response to a volumetric change below a pre-determined threshold. | 12-22-2011 |
20120011086 | SYSTEMS AND METHODS FOR SEQUENCE DATA ALIGNMENT QUALITY ASSESSMENT - A computer-implemented method for classifying alignments of paired nucleic acid sequence reads is disclosed. A plurality of paired nucleic acid sequence reads is received, wherein each read is comprised of a first tag and a second tag separated by an insert region. Potential alignments for the first and second tags of each read to a reference sequence is determined, wherein the potential alignments satisfies a minimum threshold mismatch constraint. Potential paired alignments of the first and second tags of each read are identified, wherein a distance between the first and second tags of each potential paired alignment is within an estimated insert size range. An alignment score is calculated for each potential paired alignment based on a distance between the first and second tags and a total number of mismatches for each tag. | 01-12-2012 |
20120023049 | OPERATING ABILITY MONITORING SYSTEM - An operating ability monitoring system that includes a person-dependent acceleration sensor, a telemetry unit, and an evaluation unit, wherein the person-dependent acceleration sensor and the telemetry unit may be worn by and/or implanted in a machine operator and connected to the evaluation unit, and wherein the evaluation unit is configured to receive acceleration values originating from the person-dependent acceleration sensor and sensor values originating from a further sensor that reflects the movements and/or acceleration of a vehicle or moving machine and to evaluate them by comparing the acceleration values from the person-dependent acceleration sensor to the sensor values associated with the vehicle or moving machine. | 01-26-2012 |
20120023050 | CLASSIFYING AN ITEM TO ONE OF A PLURALITY OF GROUPS - A method of classifying an item to one of a plurality of groups includes providing a plurality of predictors associated with the item. For each predictor, the item is assigned to one of the groups. An assignment number is determined for each group. The item is classified to one of the groups based on the assignment number for each group. | 01-26-2012 |
20120030157 | TRAINING DATA GENERATION APPARATUS, CHARACTERISTIC EXPRESSION EXTRACTION SYSTEM, TRAINING DATA GENERATION METHOD, AND COMPUTER-READABLE STORAGE MEDIUM - The disclosed apparatus uses a training data generation apparatus | 02-02-2012 |
20120036097 | Systems And Methods For Recognizing Events - Systems and methods for recognizing events include a processor for executing machine readable instructions. The processor may be electronically coupled to an electronic memory. A temporal sensor may be electronically coupled to the processor for generating a sequence of temporal signals relating to an unrecognized event. The temporal sensor may transmit the sequence of temporal signals to the processor. The processor may execute the machine readable instructions to: input the sequence of temporal signals relating to the unrecognized event to a recurrent neural network; transform the sequence of temporal signals relating to the unrecognized event to a neural output relating to the unrecognized event with the recurrent neural network; input the neural output relating to the unrecognized event into a random forest classifier; and recognize a recognized event based upon a transformation of the neural output relating to the unrecognized event with the random forest classifier. | 02-09-2012 |
20120041915 | METHOD FOR DIAGNOSING URTICARIA AND ANGIOEDEMA - According to the invention there is provided a method for diagnosing urticaria or angioedema including: (a) asking a patient the following questions: are any NSAIDs or aspiring being taken; are symptoms triggered by aspirin, aspirin-containing drugs, orange juice, curry or high-aspirin content food; is tingling of the mouth or lips, swelling of the tongue, the inside of the mouth or throat, difficulty swallowing, or difficulty breathing experienced after other medications than those known to cause urticaria or angioedema; does urticaria or angioedema come on with physical stimuli such as cold, wet, wind and pressure; (b) carrying out one or more tests which includes a RAST test to cat; (c) inputting the results of the questions and tests into a neural network that has been trained to diagnose urticaria or angioedema; and (d) producing an output indicative of urticaria or angioedema. | 02-16-2012 |
20120089545 | DEVICE AND METHOD FOR MULTICLASS OBJECT DETECTION - The present invention provides a device and method for multiclass object detection, wherein the detection device includes: an input unit configured to input data to be detected; and a joint classifier within which a plurality of strong classifiers capable of processing multiclass object data are included, wherein each of the strong classifiers is acquired by adding a set of weak classifiers together, and each weak classifiers performs a weak classification for the data to be detected by using a feature. A list of shared features is included within the joint classifier, and each feature within the list is shared by one or more weak classifiers belonging to different strong classifiers respectively; and the weak classifiers, which use a same feature and belong to different strong classifiers respectively, have different parameter values from one another. | 04-12-2012 |
20120101966 | METHOD AND APPARATUS FOR NEUROPSYCHOLOGICAL MODELING OF HUMAN EXPERIENCE AND PURCHASING BEHAVIOR - A system for accurately modeling of buyer/purchaser psychology and ranking of content objects within a channel for user initiated browsing and presentation contains a neuropsychological modeling engine, a ranking application, and a behavior modeler which communicate with each other and a presentation system over communication networks. The neuropsychological modeling engine utilizes metafiles associated with content objects, a purchaser/viewer model and a channel model to derive a value ψ representing an individual's mood and a value m representing an individual's motivational strength to select a content object. If the value ψ is within an acceptable predetermined range, the value m is used to determine a ranking for the content object relative to other content objects associated with the channel model. Also disclosed are a system and technique for simultaneously presenting multiple, s content object data streams on the user interface in a manner which encourages multidimensional browsing using traditional navigation commands. | 04-26-2012 |
20120101967 | STATISTICAL MESSAGE CLASSIFIER - A system and method are disclosed for improving a statistical message classifier. A message may be tested with a machine classifier, wherein the machine classifier is capable of making a classification on the message. In the event the message is classifiable by the machine classifier, the statistical message classifier is updated according to the reliable classification made by the machine classifier. The message may also be tested with a first classifier. In the event that the message is not classifiable by the first classifier, it is tested with a second classifier, wherein the second classifier is capable of making a second classification. In the event that the message is classifiable by the second classifier, the statistical message classifier is updated according to the second classification. | 04-26-2012 |
20120117010 | DEVICE FOR CLASSIFYING DEFECTS AND METHOD FOR ADJUSTING CLASSIFICATION - Disclosed is a technique wherein an object that requires adjustment in order to increase the reliability of automatic classification can be easily identified. A device ( | 05-10-2012 |
20120143804 | PREDICTING ODOR PLEASANTNESS WITH AN ELECTRONIC NOSE - Apparatus and method for assessing odors, comprises an electronic nose, to be applied to an odor and to output a structure identifying the odor; a neural network which maps an extracted structure to a first location on a pre-learned axis of odor pleasantness; and an output for outputting an assessment of an applied odor based on said first location. The assessment may be a prediction of how pleasant a user will consider the odor. | 06-07-2012 |
20120143805 | Cancer Biomarkers and Uses Thereof - The present disclosure includes biomarkers, methods, devices, reagents, systems, and kits for the detection and diagnosis of cancer. In one aspect, the disclosure provides biomarkers that can be used alone or in various combinations to diagnose cancer. In another aspect, methods are provided for diagnosing cancer in an individual, where the methods include detecting, in a biological sample from an individual, at least one biomarker value corresponding to at least one biomarker selected from the group of biomarkers provided in Table 47, wherein the individual is classified as having cancer, or the likelihood of the individual having cancer is determined, based on the at least one biomarker value. | 06-07-2012 |
20120150778 | METHOD AND SYSTEM FOR DETECTING OVERLOAD AND UNLAWFUL MEASUREMENT OF VEHICLE - A method and system to detect correctly overload & unlawful loading of cargoes under any circumstance. The Detection method of wrong measurement according to this invention are configured of Practicing Phase of Artificial Intelligence Algorithm to discriminate Wrong Measured Information by false manipulation of axle from Normal Measured Information without false manipulation of axle of vehicles by Pattern Information; Recognizing entering vehicle and Collecting Phase of Basic Data of the vehicle including dead weight, maximum pay load, and axles information; Verifying Phase of current vehicle information including total weight, load on each axle, and entering speed; And Classifying Phase of Measured Status of above vehicle using above collected and verified information as input value to Artificial Intelligence Algorithm. It might be desirable that Neural Back-Propagation Algorithm is implemented to detection method of wrong measurement according to the Invent as an Artificial Intelligence Algorithm. | 06-14-2012 |
20120166376 | INFORMATION CLASSIFICATION DEVICE, INFORMATION CLASSIFICATION METHOD, AND PROGRAM FOR CLASSIFYING INFORMATION - An information classification device of the present invention includes a classifying unit ( | 06-28-2012 |
20120197831 | NOVEL WAVELET MODELING PARADIGMS FOR CARDIOVASCULAR PHYSIOLOGICAL SIGNAL INTERPRETATION - Described herein is a method of processing a cardiovascular physiological signal, comprising: decomposing the cardiovascular physiological signal into a first plurality of wavelet coefficients using a wavelet transform; selecting a second plurality of wavelet coefficients from the first plurality of wavelet coefficients, the second plurality being a subset of the first plurality; classifying or clustering the cardiovascular physiological signal into one of a plurality of predetermined classes based on the second plurality of wavelet coefficients using an artificial neural network. | 08-02-2012 |
20120203723 | Server System and Method for Network-Based Service Recommendation Enhancement - A networked server system for enabling, facilitating and accuracy enhancing personalized service recommendations to a user of a new service S | 08-09-2012 |
20120209799 | CLASSIFICATION DEVICE AND CLASSIFICATION METHOD - Provided is a classification device capable of classifying time series data of location information into groups in which continuity of time is secured. The classification device ( | 08-16-2012 |
20120254085 | INFORMATION CLASSIFICATION SYSTEM, INFORMATION PROCESSING APPARATUS, INFORMATION CLASSIFICATION METHOD AND PROGRAM - An information classification system includes a server including a knowledge base that receives classification information to be classified, conducts language analysis of the classification information to acquire and classify a plurality of keywords into elements made up of a classification target word and a related word that modifies the classification target word, and conducts a search with the related word, so as to assign a classification identification value to the information; a classification candidate extraction section that extracts the classification identification value that the knowledge base assigns to generate an automatic classification result; and a classification update section that receives the automatic classification result and corrects registered items in the knowledge base with a correction value received through a GUI for classification confirmation while referring to log data that is a processing history about automatic classification for the language analysis and the element classification. | 10-04-2012 |
20120259803 | MULTIPLE TWO-STATE CLASSIFIER OUTPUT FUSION SYSTEM AND METHOD - A system and method for providing more than two levels of classification distinction of a user state are provided. The first and second general states of a user are sensed. The first general state is classified as either a first state or a second state, and the second general state is classified as either a third state or a fourth state. The user state of the user is then classified as one of at least three different classification states. | 10-11-2012 |
20120290519 | METHOD AND APPARATUS FOR IDENTIFICATION OF LINE-OF-RESPONSES OF MULTIPLE PHOTONS IN RADIATION DETECTION MACHINES - The present disclosure relates to a method and an apparatus for identifying line-of-responses (LOR) of photons. A radiation detection machine measures the photons. LOR identification errors are then mitigated using pattern recognition of the measurements. In some embodiments, the photons may comprise positron annihilation photons, each position annihilation photon being associated with one or more scattered photons. In yet some embodiments, pattern recognition may be implemented in a neural network. | 11-15-2012 |
20120303563 | Remote Chemical Assay Classification - A portable device for remote chemical assay classification, comprising a computer processor, and an apparatus implemented on the computer processor, the apparatus comprising: an out-of-sample data receiver, configured to receive data defining an out-of-sample extension extracted on a remote computer from classifying test assays of a chemical reaction on the remote computer into at least two groups, and an assay classifier, in communication with the out-of-sample data receiver, configured to classify a new assay of the chemical reaction into one of the groups, using the data defining the out-of-sample extension. | 11-29-2012 |
20130041858 | COATING COLOR DATABASE CREATING METHOD, SEARCH METHOD USING THE DATABASE, THEIR SYSTEM, PROGRAM, AND RECORDING MEDIUM - A method for creating a database for paint colors having a desired texture includes storing spectral reflectance data and micro-brilliance data of paint colors after associating each spectral reflectance data and each micro-brilliance data with a paint color code; storing texture evaluation values of sample paint colors after associating the each texture evaluation value with the paint color code; calculating characteristic quantities of the paint colors expressing textures using the spectral reflectance data and the micro-brilliance data, and storing the characteristic quantities after associating the each characteristic quantity with the paint color code; training a neural network using the characteristic quantities and the texture evaluation values of the sample paint colors as training data; and inputting characteristic quantities of the paint colors other than the sample paint colors into the neural network after the training, and storing output data after associating each output data with the paint color code. | 02-14-2013 |
20130110752 | On Demand Multi-Objective Network Optimization | 05-02-2013 |
20130117206 | DYNAMIC TRAINING AND TAGGING OF COMPUTER CODE - System, method, device and article of manufacture are provided wherein software code is sorted between optional pools using attributes of software in the target pools. Training for subsequent sorts can take place when attributes of already sorted code is considered and used when sorting previously unclassified code. Manual intervention may also be used to sort code and to verify the accuracy of previous sorts. | 05-09-2013 |
20130117207 | METHOD OF CLASSIFYING INPUT PATTERN AND PATTERN CLASSIFICATION APPARATUS - A method of classifying an input pattern and a pattern classification apparatus are provided. The method includes enabling an artificial neural network to learn based on learning input data received by an input layer of the artificial neural network, determining classification of an input pattern received by the input layer of the enabled artificial neural network according to an output value obtained from an output layer of the artificial neural network, the obtained output value being based on the input pattern, updating connection intensities of a plurality of connection lines of the enabled artificial neural network to output a result value indicating the determined classification from the output layer when the input pattern, and determining updated classification of the input pattern according to an updated output value obtained from an output layer of the updated artificial neural network, the obtained updated output value being based on the input pattern. | 05-09-2013 |
20130132315 | CLASSIFICATION USING CORRENTROPY - Various methods and systems are provided for classification using correntropy. In one embodiment, a classifying device includes a processing unit and memory storing instructions in modules that when executed by the processing unit cause the classifying device to adaptively classify a data value using a correntropy loss function. In another embodiment, a method includes adjusting a weight of a classifier based at least in part on a change in a correntropy loss function signal and classifying a data value using the classifier. In another embodiment, a method includes classifying a data value by predicting a label for the data value using a discriminant function, determining a correntopy statistical similarity between the predicted label and an actual label based at least in part on a correntropy loss function, and minimizing an expected risk associated with the predicted label based at least in part on a correntropy statistical similarity. | 05-23-2013 |
20130159230 | Data Forgetting System - A system and method for forgetting data in a navigation system is disclosed. The system comprises a monitor module, a determination module and a delete module. The monitor module detects a trigger event. The determination module determines a classification for the trigger event. The determination module determines a set of learning parameters to delete from a memory associated with a navigation system based at least in part on detection of the trigger event and the classification of the trigger event. The delete module deletes the determined set of learning parameters. | 06-20-2013 |
20130166485 | AUTOMATED OBSERVATIONAL DECISION TREE CLASSIFIER - Various embodiments of systems and methods for automatic classification of objects in a computer system are described herein. A class decision is received, where the class decision is a classification of an object from a number of objects to a class from a number of classes. The class decision is classification of the object by a role model. An exploration tree is expanded based on the class decision. A decision tree is constructed based on the exploration tree. Objects are classified based on said decision tree. | 06-27-2013 |
20130173514 | Automated Network Disturbance Prediction System Method & Apparatus - An apparatus and method are provided for generating a prediction warning when an operational disturbance is detected in a computer, software program or in network. A classifying portion classifies problems or outages according to an impact that the problem or the outage has on the computer, software program or network. An analysis portion analyzes data and establishes links between isolated computer, software or network problems or outages, and outputs a likely cost of a future computer, software or network problem or outage. A reporting portion reports the prediction warning in response to the likelihood of the computer, software or future network problem or outage in a format that is selected based on a type of user. | 07-04-2013 |
20130185236 | MONITORING DATA ANALYZING APPARATUS, MONITORING DATA ANALYZING METHOD, AND MONITORING DATA ANALYZING PROGRAM - An object of the present invention is to reduce a prediction error even if a monitoring target system has a plurality of patterns of use. A monitoring data analyzing apparatus includes a log data file | 07-18-2013 |
20130218820 | Intelligent grouping system and method for mobile terminal contact directory - Disclosed is an intelligent grouping system and method thereof for a mobile terminal contact directory. The method may comprise connecting a client to a server in a wireless or wired manner to form an intelligent recognition system; synchronizing a contact directory of the client with the server; discovering, by the client, an event and extracting data information in the discovered event; analyzing, by the intelligent recognition system, the extracted data information, and automatically grouping the contact directory of the client according to the data information, the grouping information being synchronized between the client and the server through communication link; storing a contact directory grouping result in a database of the server; and displaying the grouping information on the client. | 08-22-2013 |
20130232097 | CONTINUOUS-WEIGHT NEURAL NETWORKS - A computer-based multi-layer artificial network named Continuous-weight neural network (CWNN) configured to receive an input feature set wherein the input feature set comprises a variable number of features is disclosed. A method for classifying input sets based on a trained CWNN is also disclosed. Various implementation examples are also provided. | 09-05-2013 |
20130238538 | Systems and Methods for Adaptive Smart Environment Automation - Several embodiments of systems and methods for adaptive smart environment automation are described herein. In one embodiment, a computer implemented method includes determining a plurality of sequence patterns of data points in a set of input data corresponding to a plurality of sensors in a space. The input data include a plurality of data points corresponding to each of the sensors, and the sequence patterns are at least partially discontinuous. The method also includes generating a plurality of statistical models based on the plurality of sequence patterns, and the individual statistical models corresponding to an activity of a user. The method further includes recognizing the activity of the user based on the statistical models and additional input data from the sensors. | 09-12-2013 |
20130262356 | METHOD FOR CLASSIFYING BIOMETRIC DATA - Methods, systems, and computer program products for biometric authentication and more particularly to a method for classifying biometric data consisting in constructing, on the basis of a first universal statistical model and based on a set of first individual collections of biometric data, a second statistical model comprising a plurality of statistical sub-models and taking into consideration the biometric specificities of an individual or class of individuals, such that the first and second statistical models jointly define a highly discriminatory universal statistical model. | 10-03-2013 |
20130297539 | SPIKING NEURAL NETWORK OBJECT RECOGNITION APPARATUS AND METHODS - Apparatus and methods for feedback in a spiking neural network. In one approach, spiking neurons receive sensory stimulus and context signal that correspond to the same context. When the stimulus provides sufficient excitation, neurons generate response. Context connections are adjusted according to inverse spike-timing dependent plasticity. When the context signal precedes the post synaptic spike, context synaptic connections are depressed. Conversely, whenever the context signal follows the post synaptic spike, the connections are potentiated. The inverse STDP connection adjustment ensures precise control of feedback-induced firing, eliminates runaway positive feedback loops, enables self-stabilizing network operation. In another aspect of the invention, the connection adjustment methodology facilitates robust context switching when processing visual information. When a context (such an object) becomes intermittently absent, prior context connection potentiation enables firing for a period of time. If the object remains absent, the connection becomes depressed thereby preventing further firing. | 11-07-2013 |
20130304683 | Artificial Neural Networks based on a Low-Order Model of Biological Neural Networks - A low-order model (LOM) of biological neural networks and its mathematical equivalents including the clusterer interpreter probabilistic associative memory (CIPAM) are disclosed. They are artificial neural networks (ANNs) organized as networks of processing units (PUs), each PU comprising artificial neuronal encoders, synapses, spiking/nonspiking neurons, and a scheme for maximal generalization. If the weights in the artificial synapses in a PU have been learned (and then fixed) or can be adjusted by the unsupervised accumulation rule and the unsupervised covariance rule (or supervised covariance rule), the PU is called unsupervised (or supervised) PU. The disclosed ANNs, with these Hebbian-type learning rules, can learn large numbers of large input vectors with temporally/spatially hierarchical causes with ease and recognize such causes with maximal generalization despite corruption, distortion and occlusion. An ANN with a network of unsupervised PUs (called clusterer) and offshoot supervised PUs (called interpreter) is an architecture for many applications. | 11-14-2013 |
20130304684 | SYSTEMS AND METHODS FOR A COMPUTER UNDERSTANDING MULTI MODAL DATA STREAMS - Systems and methods for understanding (imputing meaning to) multi modal data streams may be used in intelligent surveillance and allow a) real-time integration of streaming data from video, audio, infrared and other sensors; b) processing of the results of such integration to obtain understanding of the situation as it unfolds; c) assessing the level of threat inherent in the situation; and d) generating of warning advisories delivered to appropriate recipients as necessary for mitigating the threat. The system generates understanding of the system by creating and manipulating models of the situation as it unfolds. The creation and manipulation involve “neuronal packets” formed in mutually constraining associative networks of four basic types. The process is thermodynamically driven, striving to produce a minimal number of maximally stable models. Obtaining such models is experienced as grasping, or understanding the input stream (objects, their relations and the flow of changes). | 11-14-2013 |
20130325770 | PROBABILISTIC LANGUAGE MODEL IN CONTEXTUAL NETWORK - A method and apparatus for detection of relationships between objects in a meta-model semantic network is described. Semantic objects and semantic relations of a meta-model of business objects are generated from a meta-model semantic network. The semantic relations are based on connections between the semantic objects. A probability model of terminology usage in the semantic objects and the semantic relations is generated. A neural network is formed based on usage of the semantic objects, the semantic relations, and the probability model. The neural network is integrated with the semantic objects, the semantic relations, and the probability model to generate a contextual network. The generated probability model is integrated with semantic objects and neural networks for form parallel networks. | 12-05-2013 |
20130325771 | NEW CLASSIFICATION METHOD FOR SPECTRAL DATA - The present invention relates to a new method for classification of spectral data comprising:
| 12-05-2013 |
20130325772 | Event Monitoring Devices and Methods | 12-05-2013 |
20130332401 | DOCUMENT EVALUATION APPARATUS, DOCUMENT EVALUATION METHOD, AND COMPUTER-READABLE RECORDING MEDIUM - In order to accurately learn a function for evaluating documents, even in the case where sample documents having missing feature values are included as training data, a document evaluation apparatus is provided with a data classification unit ( | 12-12-2013 |
20130346350 | COMPUTER-IMPLEMENTED SEMI-SUPERVISED LEARNING SYSTEMS AND METHODS - Computer-implemented systems and methods for determining a subset of unknown targets to investigate. For example, a method can be configured to receive a target data set, wherein the target data set includes known targets and unknown targets. A supervised model such as a neural network model is generated using the known targets. The unknown targets are used with the neural network model to generate values for the unknown targets. Analysis with an unsupervised model is performed using the target data set in order to determine which of the unknown targets are outliers. A comparison of list of outlier unknown targets is performed with the values for the unknown targets that were generated by the neural network model. The subset of unknown targets to investigate is determined based upon the comparison. | 12-26-2013 |
20140046883 | METHOD AND APPARATUS FOR NEUROPSYCHOLOGICAL MODELING OF HUMAN EXPERIENCE AND PURCHASING BEHAVIOR - A system for accurately modeling of buyer/purchaser psychology and ranking of content objects within a channel for user initiated browsing and presentation contains a neuropsychological modeling engine, a ranking application, and a behavior modeler which communicate with each other and a presentation system over communication networks. The neuropsychological modeling engine utilizes metafiles associated with content objects, a purchaser/viewer model and a channel model to derive a value ψ representing an individual's mood and a value m representing an individual's motivational strength to select a content object. If the value ψ is within an acceptable predetermined range, the value m is used to determine a ranking for the content object relative to other content objects associated with the channel model. Also disclosed are a system and technique for simultaneously presenting multiple, s content object data streams on the user interface in a manner which encourages multidimensional browsing using traditional navigation commands. | 02-13-2014 |
20140046884 | APPARATUS, METHOD, AND PROGRAM FOR EXTRACTING CONTENT-RELATED POSTS - To achieve accurate classification of posts into related and unrelated ones in a short time and at low cost by performing automatic data labeling in supervised learning. An apparatus for extracting content-related posts, including a microblog collection section that collects posts by using an API provided by the microblog, a classification section that classifies titles into titles having multiple meanings and titles not having multiple meanings, and a microblog relevance determination section that determines the relevance of posts to content depending on whether the title has multiple meanings. | 02-13-2014 |
20140067735 | COMPUTER-IMPLEMENTED DEEP TENSOR NEURAL NETWORK - A deep tensor neural network (DTNN) is described herein, wherein the DTNN is suitable for employment in a computer-implemented recognition/classification system. Hidden layers in the DTNN comprise at least one projection layer, which includes a first subspace of hidden units and a second subspace of hidden units. The first subspace of hidden units receives a first nonlinear projection of input data to a projection layer and generates the first set of output data based at least in part thereon, and the second subspace of hidden units receives a second nonlinear projection of the input data to the projection layer and generates the second set of output data based at least in part thereon. A tensor layer, which can converted into a conventional layer of a DNN, generates the third set of output data based upon the first set of output data and the second set of output data. | 03-06-2014 |
20140067736 | METHODS AND SYSTEMS FOR POWER MANAGEMENT IN A PATTERN RECOGNITION PROCESSING SYSTEM - A device includes a state machine. The state machine includes a plurality of blocks, where each of the blocks includes a plurality of rows. Each of these rows includes a plurality of programmable elements. Furthermore, each of the programmable elements are configured to analyze at least a portion of a data stream and to selectively output a result of the analysis. Each of the plurality of blocks also has corresponding block activation logic configured to dynamically power-up the block. | 03-06-2014 |
20140067737 | Multivariate Transaction Classification - Embodiments relate to classification of transactions based upon analysis of multiple variables. For a purchase transaction, such variables can include but are not limited to: buying location, source system, line of business, cost center, functional area, supplier capabilities, item description, account description, organization, department, custom parameters, and others. Embodiments may rely upon one or more classification schemes, such as statistical classification, semantic classification, and/or knowledge base classification, taken alone or in combination. In a purchase transaction, classification based on multivariate analysis facilitates identification of a purchased item or service, and hence accuracy in classifying and assigning a central classification code. Particular embodiments may include a feature allowing user review/revision of category assignments via a feedback loop linked to past classification. This revision feature may add clarity to a current transaction, allow modification of future classification for ongoing improvement, and provide a user-driven measure of system performance. | 03-06-2014 |
20140067738 | Training Deep Neural Network Acoustic Models Using Distributed Hessian-Free Optimization - A method for training a neural network includes receiving labeled training data at a master node, generating, by the master node, partitioned training data from the labeled training data and a held-out set of the labeled training data, determining a plurality of gradients for the partitioned training data, wherein the determination of the gradients is distributed across a plurality of worker nodes, determining a plurality of curvature matrix-vector products over the plurality of samples of the partitioned training data, wherein the determination of the plurality of curvature matrix-vector products is distributed across the plurality of worker nodes, and determining, by the master node, a second-order optimization of the plurality of gradients and the plurality of curvature matrix-vector products, producing a trained neural network configured to perform a structured classification task using a sequence-discriminative criterion. | 03-06-2014 |
20140108313 | RANKING IN CASCADING LEARNING SYSTEM - A ranking in cascading learning system is described. The cascading learning system has a request analyzer, a request dispatcher and classifier, a search module, a terminology manager, and a cluster manager. The request analyzer receives a request for search terms from a client application and determines term context in the request to normalize request data from the term context. The normalized request data are classified and dispatched to a corresponding domain-specific module with a request dispatcher ranking calibrator. Each domain-specific module of a search module generates a prediction with a trained probability of an expected output using a corresponding domain-specific ranking calibrator. The terminology manager receives normalized request data from the request dispatcher and classifier, and manages terminology stored in a contextual network. The cluster manager comprises a central ranking calibrator, a training and sot container, and a module generator configured to generate a pluggable module. | 04-17-2014 |
20140108314 | INTEGRATED APPROACH TO MODEL TIME SERIES DYNAMICS IN COMPLEX PHYSICAL SYSTEMS - A system and method for analysis of complex systems which includes determining model parameters based on time series data, further including profiling a plurality of types of data properties to discover complex data properties and dependencies; classifying the data dependencies into predetermined categories for analysis; and generating a plurality of models based on the discovered properties and dependencies. The system and method may analyze, using a processor, the generated models based on a fitness score determined for each model to generate a status report for each model; integrate the status reports for each model to determine an anomaly score for the generated models; and generate an alarm when the anomaly score exceeds a predefined threshold. | 04-17-2014 |
20140114892 | APPARATUS AND METHODS OF ANALYSIS OF PIPE AND ANNULUS IN A WELLBORE - Various embodiments include apparatus and methods to provide pipe analysis, annulus analysis, or one or more combinations of pipe analysis and annulus analysis with respect to one or more pipes in a wellbore. The analysis can include application of clustering and classification methods with respect to the status and the environment of the one or more pipes in the wellbore. In various embodiments, the clustering and classification can be used in characterizing borehole annular material including cement bond quality evaluation. Additional apparatus, systems, and methods are disclosed. | 04-24-2014 |
20140122401 | System and Method for Combining Segmentation Data - Systems and methods are provided for combining multiple segmentations into a single unique segmentation that contains attributes of the original segmentations. This new segmentation forms an ensemble or combination segmentation that has a unique set of attributes from the original segmentations without enumerating every possible set of combinations. In one example, two or more segments are combined into a single segmentation using a technique such as k-means clustering or Self-Organizing Map Neural Networks. After the first combination phase is performed, a Bayesian technique is then applied in a second phase to adjust or further alter the ensemble combination of segments. | 05-01-2014 |
20140172761 | TIME SERIES CLASSIFYING MEMORY, SYSTEMS AND METHODS - A time series classifying memory includes an enumerated group of synapses. Each synapse of the group has a junction including pre-synaptic emitters communicating with post synaptic receptors. A single pathway is input to each synapse of the group, and when innervated, stimulates the junctions. Each successive synapse has successively more post synaptic receptors according to a fixed ratio. At each junction, quanta of neurotransmitter emitted from the emitters bind with available receptors. When all the receptors at a junction have been bound, the junction goes refractory. The synapse adjacent to the last junction to go refractory is marked. During a training mode the mark is a Long Term Potentiation (LTP) mark. During a live mode the mark is a Short Term Potentiation (STP) mark. The input is classified upon successful correlation of the LTP mark with the STP mark. A clock operable with synaptic matrix models this process. | 06-19-2014 |
20140201117 | USING RADIAL BASIS FUNCTION NETWORKS AND HYPER-CUBES FOR EXCURSION CLASSIFICATION IN SEMI-CONDUCTOR PROCESSING EQUIPMENT - A method and system for analysis of data, including creating a first node, determining a first hyper-cube for the first node, determining whether a sample resides within the first hyper-cube. If the sample does not reside within the first hyper-cube, the method includes determining whether the sample resides within a first hyper-sphere, wherein the first hyper-sphere has a radius equal to a diagonal of the first hyper-cube. | 07-17-2014 |
20140258196 | SYSTEM AND METHOD FOR USING GRAPH TRANSDUCTION TECHNIQUES TO MAKE RELATIONAL CLASSIFICATIONS ON A SINGLE CONNECTED NETWORK - A system and method for extending partially labeled data graphs to unlabeled nodes in a single network classification by weighting the data with a weight matrix that uses a modified graph Laplacian based regularization framework and applying graph transduction methods to the weighted data. The technique may be applied to data graphs that are directed or undirected, that may or may not have attributes and that may be homogeneous or heterogeneous. | 09-11-2014 |
20140279773 | Scoring Concept Terms Using a Deep Network - Methods, systems, and apparatus, including computer programs encoded on computer storage media, for scoring concept terms using a deep network. One of the methods includes receiving an input comprising a plurality of features of a resource, wherein each feature is a value of a respective attribute of the resource; processing each of the features using a respective embedding function to generate one or more numeric values; processing the numeric values to generate an alternative representation of the features of the resource, wherein processing the floating point values comprises applying one or more non-linear transformations to the floating point values; and processing the alternative representation of the input to generate a respective relevance score for each concept term in a pre-determined set of concept terms, wherein each of the respective relevance scores measures a predicted relevance of the corresponding concept term to the resource. | 09-18-2014 |
20140279774 | Classifying Resources Using a Deep Network - Methods, systems, and apparatus, including computer programs encoded on computer storage media, for scoring concept terms using a deep network. One of the methods includes receiving an input comprising a plurality of features of a resource, wherein each feature is a value of a respective attribute of the resource; processing each of the features using a respective embedding function to generate one or more numeric values; processing the numeric values using one or more neural network layers to generate an alternative representation of the features, wherein processing the floating point values comprises applying one or more non-linear transformations to the floating point values; and processing the alternative representation of the input using a classifier to generate a respective category score for each category in a pre-determined set of categories, wherein each of the respective category scores measure a predicted likelihood that the resource belongs to the corresponding category. | 09-18-2014 |
20140279775 | DECISION TREE INSIGHT DISCOVERY - Techniques for presenting insight into classification trees may include performing a grouping analysis to group leaf nodes of a classification tree into a significant group and an insignificant group, performing influential target category analysis to identify one or more influential target categories for the leaf nodes of the classification tree in the significant group, and presenting one or more insights into the classification tree based on the grouping analysis and the influential target category analysis. Techniques for presenting insight into regression trees may include performing a grouping analysis to group leaf nodes of a regression tree into a high group and a low group, performing unusual node detection analysis to detect one or more outlier nodes in the high group and in the low group, and presenting one or more insights into the regression tree based on the grouping analysis and the unusual node detection analysis | 09-18-2014 |
20140279776 | METHODS AND APPARATUSES FOR PROVIDING DATA RECEIVED BY A STATE MACHINE ENGINE - An apparatus can include a first state machine engine configured to receive a first portion of a data stream from a processor and a second state machine engine configured to receive a second portion of the data stream from the processor. The apparatus includes a buffer interface configured to enable data transfer between the first and second state machine engines. The buffer interface includes an interface data bus coupled to the first and second state machine engines. The buffer interface is configured to provide data between the first and second state machine engines. | 09-18-2014 |
20140317034 | DATA CLASSIFICATION - An illustrative data classifier device includes data storage and at least one processor configured to operate as a query engine and a passive classifier that is configured to predict classification labels for data. The processor is configured to determine a relationship between the data and training data with associated training classification labels. The processor is also configured to assign a weighted version of at least one of the training classification labels to at least one member of the data based on the determined relationship. An illustrative method of classifying data includes predicting classification labels for data by determining a relationship between the data and training data with associated training classification labels. A weighted version of at least one of the training classification labels is assigned to at least one member of the data based on the determined relationship. | 10-23-2014 |
20140324748 | METHOD AND APPARATUS FOR DERIVING SPATIAL PROPERTIES OF BUS STOPS AND TRAFFIC CONTROLS - A method, apparatus and computer program products are provided for automatically detecting specific locations, i.e. bus stops, stop lights, and/or traffic signals, based on received GPS reports. The method can also be adopted to detect the utilization of the specific locations along the route. One example method includes receiving GPS data from a plurality of buses from along a transit route, and utilizes a machine learning classification strategy that captures the mobility patterns of the GPS equipped buses, at specific locations. The method may then generate mini-clusters, each comprised of a first location point from a first route and one or more subsequent location points located within a predetermined distance of the first location point. The mobility patterns of the mini-clusters within larger clusters are represented as a normalized histogram where the bin values become classification features. A machine learning model is then utilized to determine a location of the specific locations. | 10-30-2014 |
20140344200 | LOW POWER INTEGRATED ANALOG MATHEMATICAL ENGINE - A method for creating on chip analog mathematical engines is provided utilizing a neural network with a switched capacitor structure to implement coefficients for weighted connections and error functions for the neural network. The neural networks are capable of any transfer function, learning, doing pattern recognition, clustering, control or many other functions. The switched capacitor charge controls allow for nodal control of charge transfer based switched capacitor circuits. The method reduces reliance on passive component programmable arrays to produce programmable switched capacitor circuit coefficients. The switched capacitor circuits are dynamically scaled without having to rely on switched in unit passives, such as unit capacitors, and the complexities of switching these capacitors into and out of circuit. The current, and thus the charge transferred is controlled at a nodal level, and the current rather than the capacitors are scaled providing a more accurate result in addition to saving silicon area. | 11-20-2014 |
20140351186 | SPIKE TIME WINDOWING FOR IMPLEMENTING SPIKE-TIMING DEPENDENT PLASTICITY (STDP) - Methods and apparatus are provided for implementing spike-timing dependent plasticity (STDP) using windowing of spikes. One example method for operating an artificial nervous system generally includes recording spike times for a first artificial neuron, recording spike times for a second artificial neuron coupled to the first artificial neuron via a synapse, processing spikes for the second artificial neuron according to a window based at least in part on the spike times for the first artificial neuron, and updating a parameter (e.g., a weight or a delay) of the synapse based on the processing. | 11-27-2014 |
20150012472 | SYSTEMS, METHODS, AND MEDIA FOR UPDATING A CLASSIFIER - Systems, methods, and media for updating a classifier are provided, in some embodiments, systems for updating a classifier are provided, the systems comprising: a hardware processor that is configured to: receive a sample; for each of a first plurality of weak learners, classify the sample using the weak learner, determine an outcome of the classification, and determine an up-dated error rate of the weak learner based on the outcome of the classification and at least one of: (i) a count of positive samples used to update the classifier, and (ii) a count of negative samples used to update the classifier; select a first weak learner from the first plurality of weak learners based on the updated error rate of the first weak learner; and update tire classifier based on the first weak learner. | 01-08-2015 |
20150039543 | Feature Based Three Stage Neural Network Intrusion Detection - A system for detecting a network intrusion includes a first neural network for determining a first plurality of weight values corresponding to a plurality of vectors of an input data, a second neural network for updating the first plurality of weight values received from the first neural network to a second plurality of weight values based on the plurality of vectors of the input data, a third neural network for updating the second plurality of weight values received from the second neural network to a third plurality of weight values based on the plurality of vectors of the input data, and a classification module for classifying the plurality of vectors under at least one of a plurality of intrusions based on the third plurality of weight values received from the third neural network. | 02-05-2015 |
20150066825 | SIMULATED INFRARED MATERIAL COMBINATION USING NEURAL NETWORK - Mipping systems and methods are disclosed. For example, a mipping system can include processing circuitry configured to receive combinations of a plurality of pixels N at a time, each pixel having material codes directed to respective materials of the pixels, where the material codes relate to infrared properties of the respective materials, and N is a positive integer greater than 1; and train an artificial neural network having a classification space by providing respective neurons for each unique combination of material codes, and condition the artificial neural network so that the respective neurons activate when presented with their unique of material code combinations in order to create a combined set of material code parameters for accurate rendering of the mipped pixels. | 03-05-2015 |
20150100527 | Methods and Systems for Analysis and/or Classification of Information - Methods and systems for analysis and/or classification of electronic message information so as to capture and identify salient objects exchanged during electronic message passing in order to impute certain information about the object, groups of objects, the message, groups of messages, the parties, communities involved in the message exchange or combinations, thereof. | 04-09-2015 |
20150106310 | METHOD AND APPARATUS FOR CONSTRUCTING A NEUROSCIENCE-INSPIRED ARTIFICIAL NEURAL NETWORK - A method and apparatus for constructing a neuroscience-inspired dynamic architecture (NIDA) for an artificial neural network is disclosed. The method comprises constructing, in one embodiment, an artificial neural network embodiment in a multi-dimensional space in memory such that a neuron is connected by a synapse to another neuron. The neuron and the synapse each have parameters and have features of long-term potentiation and long-term depression. Furthermore, crossover and mutation are employed to select children of parents. Through learning, an initial network may evolve into a different network when NIDA is applied to solve different problems of control, anomaly detection and classification over selected time units. The apparatus comprises in one embodiment a computational neuroscience-inspired artificial neural network with at least one affective network coupled to receive input data from an environment and to output data to the environment. | 04-16-2015 |
20150106311 | METHOD AND APPARATUS FOR CONSTRUCTING, USING AND REUSING COMPONENTS AND STRUCTURES OF AN ARTIFICAL NEURAL NETWORK - A method and apparatus for constructing a neuroscience-inspired artificial neural network (NIDA) or a dynamic adaptive neural network array (DANNA) or combinations of substructures thereof comprises one of constructing a substructure of an artificial neural network for performing a subtask of the task of the artificial neural network or extracting a useful substructure based on one of activity, causality path, behavior and inputs and outputs. The method includes identifying useful substructures in artificial neural networks that may be either successful at performing a subtask or unsuccessful at performing a subtask. Successful substructures may be implanted in an artificial neural network and unsuccessful substructures may be extracted from the artificial neural network for performing the task. The method and apparatus supports constructing, using and reusing components and structures of a neuroscience-inspired artificial neural network dynamic architecture in software and a dynamic adaptive neural network array. | 04-16-2015 |
20150120626 | METHODS AND APPARATUS FOR TAGGING CLASSES USING SUPERVISED LEARNING - Certain aspects of the present disclosure provide methods and apparatus for creating tags (static or dynamic) for input/output classes of a neural network model using supervised learning. The method includes augmenting a neural network model with a plurality of neurons and training the augmented network using spike timing dependent plasticity (STDP) to determine one or more tags. | 04-30-2015 |
20150120627 | CAUSAL SALIENCY TIME INFERENCE - Methods and apparatus are provided for causal learning in which logical causes of events are determined based, at least in part, on causal saliency. One example method for causal learning generally includes observing one or more events with an apparatus, wherein the events are defined as occurrences at particular relative times; selecting a subset of the events based on one or more criteria; and determining a logical cause of at least one of the events based on the selected subset. | 04-30-2015 |
20150324688 | CUSTOMIZED CLASSIFIER OVER COMMON FEATURES - A method of generating a classifier model includes distributing a common feature model to two or more users. Multiple classifiers are trained on top of the common feature model. The method further includes distributing a first classifier of the multiple classifiers to a first user and a second classifier of the multiple classifiers to a second user. | 11-12-2015 |
20150324689 | CUSTOMIZED CLASSIFIER OVER COMMON FEATURES - A method of updating a set of classifiers includes applying a first set of classifiers to a first set of data. The method further includes requesting, from a remote device, a classifier update based on an output of the first set of classifiers or a performance measure of the application of the first set of classifiers. | 11-12-2015 |
20150371132 | METHODS AND APPARATUS FOR TRAINING AN ARTIFICIAL NEURAL NETWORK FOR USE IN SPEECH RECOGNITION - Methods and apparatus for training a multi-layer artificial neural network for use in speech recognition. The method comprises determining for a first speech pattern of the plurality of speech patterns, using a first processing pipeline, network activations for a plurality of nodes of the artificial neural network in response to providing the first speech pattern as input to the artificial neural network, determining based, at least in part, on the network activations and a selection criterion, whether the artificial neural network should be trained on the first speech pattern, and updating, using a second processing pipeline, network weights between nodes of the artificial neural network based, at least in part, on the network activations when it is determined that the artificial neural network should be trained on the first speech pattern. | 12-24-2015 |
20150379394 | DEVICE AND METHOD FOR THE AUTONOMOUS BOOTSTRAPPING OF UNIFIED SENTIENCE - A system for monitoring an environment may include an input device for monitoring and capturing pattern-based states of a model of the environment. The system may also include a 5 thalamobot embodied in at least a first processor, in which the first processor is in communication with the input device. The thalamobot may include at least one filter for monitoring captured data from the input device and for identifying at least one state change within the captured data. The system may also include at least one critic and/or at least one recognition system. | 12-31-2015 |
20150379397 | SECURE VOICE SIGNATURE COMMUNICATIONS SYSTEM - Embodiments of the present invention provides a system and a method for connecting two or more parts of a distributed and spatio-temporal spiking neural network by a means of communication, such as the Internet, used for recognizing and identifying acoustic signals using acoustic signature recognition by means of a spatio-temporal neural network. The first artificial intelligent device identifies features in a series of spatio-temporal pulse streams received from an artificial cochlear, and learns to respond to the pulse streams. The features of the pulse stream identifying an event learned by the first artificial intelligent device are transmitted to the remote artificial intelligent device over a communication protocol via a Series Address Event Representation bus, where the remote artificial intelligent device learns to respond. Further, a computing device may be connected to the remote artificial intelligent device for analyzing and controlling one or more appliances from anywhere in the world. | 12-31-2015 |
20160004961 | FEATURE EXTRACTION USING A NEUROSYNAPTIC SYSTEM - Embodiments of the invention provide a neurosynaptic system comprising a first set of one or more neurosynaptic core circuits configured to receive input data comprising multiple input regions, and extract a first set of features from the input data. The features of the first set are computed based on different input regions. The system further comprises a second set of one or more neurosynaptic core circuits configured to receive the first set of features, and generate a second set of features by combining the first set of features based on synaptic connectivity information of the second set of core circuits. | 01-07-2016 |
20160004962 | CLASSIFYING FEATURES USING A NEUROSYNAPTIC SYSTEM - Embodiments of the invention provide a method comprising receiving a set of features extracted from input data, training a linear classifier based on the set of features extracted, and generating a first matrix using the linear classifier. The first matrix includes multiple dimensions. Each dimension includes multiple elements. Elements of a first dimension correspond to the set of features extracted. Elements of a second dimension correspond to a set of classification labels. The elements of the second dimension are arranged based on one or more synaptic weight arrangements. Each synaptic weight arrangement represents effective synaptic strengths for a classification label of the set of classification labels. The neurosynaptic core circuit is programmed with synaptic connectivity information based on the synaptic weight arrangements. The core circuit is configured to classify one or more objects of interest in the input data | 01-07-2016 |
20160012331 | SCORING CONCEPT TERMS USING A DEEP NETWORK | 01-14-2016 |
20160026915 | Methods and Apparatus for Data Analysis - A method and apparatus for data analysis according to various aspects of the present invention is configured to test a set of components and generate test data for the components. A diagnostic system automatically analyzes the test data to identify a characteristic of a component fabrication process by recognizing a pattern in the test data and classifying the pattern using a neural network. | 01-28-2016 |
20160034809 | SYSTEM AND METHOD FOR NETWORK BASED APPLICATION DEVELOPMENT AND IMPLEMENTATION - An application provisioning system and method. A server provides an application provisioning service. A user of a client provides a schema defining an application. The application interacts with peripherals coupled to the client and receives input from sensors coupled to the peripherals. The sensor data is provided to the server for processing, including by neural networks. The application includes a workflow defining a finite state machine that traverses states at least partially based on the response to sensor data. The server may provide dynamic reallocation of compute resources to resolve demand for classifier training job requests; use of jurisdictional certificates to define data usage and sharing; and data fusion. Applications include manufacturing verification, medical diagnosis and treatment, genomics and viral detection. | 02-04-2016 |
20160034811 | EFFICIENT GENERATION OF COMPLEMENTARY ACOUSTIC MODELS FOR PERFORMING AUTOMATIC SPEECH RECOGNITION SYSTEM COMBINATION - Systems and processes for generating complementary acoustic models for performing automatic speech recognition system combination are provided. In one example process, a deep neural network can be trained using a set of training data. The trained deep neural network can be a deep neural network acoustic model. A Gaussian-mixture model can be linked to a hidden layer of the trained deep neural network such that any feature vector outputted from the hidden layer is received by the Gaussian-mixture model. The Gaussian-mixture model can be trained via a first portion of the trained deep neural network and using the set of training data. The first portion of the trained deep neural network can include an input layer of the deep neural network and the hidden layer. The first portion of the trained deep neural network and the trained Gaussian-mixture model can be a Deep Neural Network-Gaussian-Mixture Model (DNN-GMM) acoustic model. | 02-04-2016 |
20160048754 | CLASSIFYING RESOURCES USING A DEEP NETWORK - Methods, systems, and apparatus, including computer programs encoded on computer storage media, for scoring concept terms using a deep network. One of the methods includes receiving an input comprising a plurality of features of a resource, wherein each feature is a value of a respective attribute of the resource; processing each of the features using a respective embedding function to generate one or more numeric values; processing the numeric values using one or more neural network layers to generate an alternative representation of the features, wherein processing the floating point values comprises applying one or more non-linear transformations to the floating point values; and processing the alternative representation of the input using a classifier to generate a respective category score for each category in a pre-determined set of categories, wherein each of the respective category scores measure a predicted likelihood that the resource belongs to the corresponding category. | 02-18-2016 |
20160048756 | NEURAL NETWORK BASED CLUSTER VISUALIZATION - A computing device presents a cluster visualization based on a neural network computation. First centroid locations are computed for first clusters. Second centroid locations are computed for second clusters. Each centroid location includes a plurality of coordinate values where each coordinate value relates to a single variable of a plurality of variables. Distances are computed pairwise between each centroid location. An optimum pairing is selected based on a minimum distance of the computed pairwise distances where each pair is associated with a different cluster of a set of composite clusters. Noised centroid location data is created. A multi-layer neural network is trained with the noised centroid location data. A projected centroid location is determined in a multidimensional space for each centroid location as values of hidden units of a middle layer of the multi-layer neural network. A graph is presented for display that indicates the determined, projected centroid locations. | 02-18-2016 |
20160055409 | KNOWLEDGE-GRAPH BIASED CLASSIFICATION FOR DATA - A method for classifying an object includes applying multiple confidence values to multiple objects. The method also includes determining a metric based on the multiple confidence values. The method further includes determining a classification of a first object from the multiple objects based on a knowledge-graph when the metric is above a threshold. | 02-25-2016 |
20160063372 | SYSTEMS AND METHODS FOR ENHANCING COMPUTER ASSISTED HIGH THROUGHPUT SCREENING PROCESSES - Embodiments are directed to identifying active compounds for a targeted medium from a library of compounds. In one scenario, a computer system receives high throughput screening (HTS) data for a subset of compounds that have been HTS-screened. The computer system determines labels for a subset of compounds based on labels identified in the HTS-screened compounds as being part of an active class or part of an inactive class, access chemical features corresponding to the HTS-screened compounds, apply Fuzzy logic membership functions to calculate membership values for active and inactive compounds to determine the degree to which each compound belongs to the active class or to the inactive class, train an artificial neural network (ANN) to identify active compounds in silico based on the Fuzzy logic membership functions, and process another subset of compounds in silico to identify active and inactive compounds using the trained artificial neural network. | 03-03-2016 |
20160078339 | Learning Student DNN Via Output Distribution - Systems and methods are provided for generating a DNN classifier by “learning” a “student” DNN model from a larger more accurate “teacher” DNN model. The student DNN may be trained from un-labeled training data because its supervised signal is obtained by passing the un-labeled training data through the teacher DNN. In one embodiment, an iterative process is applied to train the student DNN by minimize the divergence of the output distributions from the teacher and student DNN models. For each iteration until convergence, the difference in the output distributions is used to update the student DNN model, and output distributions are determined again, using the unlabeled training data. The resulting trained student model may be suitable for providing accurate signal processing applications on devices having limited computational or storage resources such as mobile or wearable devices. In an embodiment, the teacher DNN model comprises an ensemble of DNN models. | 03-17-2016 |
20160092766 | LOW-RANK HIDDEN INPUT LAYER FOR SPEECH RECOGNITION NEURAL NETWORK - Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a deep neural network. One of the methods for training a deep neural network that includes a low rank hidden input layer and an adjoining hidden layer, the low rank hidden input layer including a first matrix A and a second matrix B with dimensions i×m and m×o, respectively, to identify a keyword includes receiving a feature vector including i values that represent features of an audio signal encoding an utterance, determining, using the low rank hidden input layer, an output vector including o values using the feature vector, determining, using the adjoining hidden layer, another vector using the output vector, determining a confidence score that indicates whether the utterance includes the keyword using the other vector, and adjusting weights for the low rank hidden input layer using the confidence score. | 03-31-2016 |
20160117587 | HIERARCHICAL DEEP CONVOLUTIONAL NEURAL NETWORK FOR IMAGE CLASSIFICATION - Hierarchical branching deep convolutional neural networks (HD-CNNs) improve existing convolutional neural network (CNN) technology. In a HD-CNN, classes that can be easily distinguished are classified in a higher layer coarse category CNN, while the most difficult classifications are done on lower layer fine category CNNs. Multinomial logistic loss and a novel temporal sparsity penalty may be used in HD-CNN training. The use of multinomial logistic loss and a temporal sparsity penalty causes each branching component to deal with distinct subsets of categories. | 04-28-2016 |
20160140436 | Face Detection Using Machine Learning - A disclosed face detection system (and method) is based on a structure of a convolutional neural network (CNN). One aspect concerns a method for automatically training a CNN for face detection. The training is performed such that balanced number of face images and non-face images are used for training by deriving additional face images from the face images. The training is also performed by adaptively changing a number of trainings of a stage according to automatic stopping criteria. Another aspect concerns a system for performing image detection by integrating data at different scales (i.e., different image extents) for better use of data in each scale. The system may include CNNs automatically trained using the method disclosed herein. | 05-19-2016 |
20160162778 | USING RADIAL BASIS FUNCTION NETWORKS AND HYPER-CUBES FOR EXCURSION CLASSIFICATION IN SEMI-CONDUCTOR PROCESSING EQUIPMENT - A method and system for analysis of data, including creating a first node, determining a first hyper-cube for the first node, determining whether a sample resides within the first hyper-cube. If the sample does not reside within the first hyper-cube, the method includes determining whether the sample resides within a first hyper-sphere, wherein the first hyper-sphere has a radius equal to a diagonal of the first hyper-cube. | 06-09-2016 |
20160180162 | GENERATING PREFERENCE INDICES FOR IMAGE CONTENT | 06-23-2016 |
20160180215 | GENERATING PARSE TREES OF TEXT SEGMENTS USING NEURAL NETWORKS | 06-23-2016 |
20160379113 | TRAINING MULTIPLE NEURAL NETWORKS WITH DIFFERENT ACCURACY - Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a deep neural network. One of the methods includes generating a plurality of feature vectors that each model a different portion of an audio waveform, generating a first posterior probability vector for a first feature vector using a first neural network, determining whether one of the scores in the first posterior probability vector satisfies a first threshold value, generating a second posterior probability vector for each subsequent feature vector using a second neural network, wherein the second neural network is trained to identify the same key words and key phrases and includes more inner layer nodes than the first neural network, and determining whether one of the scores in the second posterior probability vector satisfies a second threshold value. | 12-29-2016 |
20160379114 | METHODS AND SYSTEMS FOR DATA ANALYSIS IN A STATE MACHINE - A device includes a match element that includes a first data input configured to receive a first result, wherein the first result is of an analysis performed on at least a portion of a data stream by an element of a state machine. The match element also includes a second data input configured to receive a second result, wherein the second result is of an analysis performed on at least a portion of the data stream by another element of the state machine. The match element further includes an output configured to selectively provide the first result or the second result. | 12-29-2016 |
20170236055 | ACCURATE TAG RELEVANCE PREDICTION FOR IMAGE SEARCH | 08-17-2017 |
20190146590 | ACTION EVALUATION MODEL BUILDING APPARATUS AND ACTION EVALUATION MODEL BUILDING METHOD THEREOF | 05-16-2019 |
20190147317 | AUTOMATIC ASSEMBLY MATE CREATION FOR FREQUENTLY-USED COMPONENTS | 05-16-2019 |
20190147331 | Generation and Update of HD Maps Using Data from Heterogeneous Sources | 05-16-2019 |
20190147335 | Continuous Convolution and Fusion in Neural Networks | 05-16-2019 |
20190147338 | RECOGNITION METHOD, CORRESPONDING SYSTEM AND COMPUTER PROGRAM PRODUCT | 05-16-2019 |
20190147372 | Systems and Methods for Object Detection, Tracking, and Motion Prediction | 05-16-2019 |
20220138583 | HUMAN CHARACTERISTIC NORMALIZATION WITH AN AUTOENCODER - Generally discussed herein are devices, systems, and methods for. A method can include obtaining a normalizing autoencoder, the normalizing autoencoder trained based on first data samples of a template person and second data samples of a variety of people, normalizing, by the normalizing autoencoder, an input data sample by combining dynamic characteristics of a person in the input data sample with static characteristics in the first data samples, to generate normalized data, and providing the normalized data as input to a classifier model to classify the input data based on the dynamic characteristics of the input data and the static characteristics of the first data samples. | 05-05-2022 |