| Entries |
| Document | Title | Date |
|---|
| 20080208780 | System and method for evaluating documents - A system for evaluating documents may include a memory location for storing one or more software modules, and a processor for executing the one or more software modules. The one or more software modules may be configured to perform a method. The method may include receiving a baseline record and a potentially matching record. The method may also include identifying baseline record data, and identifying potentially matching record data. The method may further include comparing the baseline record data with the potentially matching record data using matching criteria. The method may also include calculating a score for the potentially matching record based on rank values and weight factors associated with the matching criteria. The score may be a measure of similarity between the baseline record data and the potentially matching record data. The method may further include determining whether a match exists between the baseline record and the potentially matching record based on the score. | 08-28-2008 |
| 20080222062 | SUPERVISED RANK AGGREGATION BASED ON RANKINGS - A method and system for rank aggregation of entities based on supervised learning is provided. A rank aggregation system provides an order-based aggregation of rankings of entities by learning weights within an optimization framework for combining the rankings of the entities using labeled training data and the ordering of the individual rankings. The rank aggregation system is provided with multiple rankings of entities. The rank aggregation system is also provided with training data that indicates the relative ranking of pairs of entities. The rank aggregation system then learns weights for each of the ranking sources by attempting to optimize the difference between the relative rankings of pairs of entities using the weights and the relative rankings of pairs of entities of the training data. | 09-11-2008 |
| 20080222063 | Extensible mechanism for detecting duplicate search items - Systems, methods, and other embodiments associated with identifying and selectively deleting duplicate search results are described. One example system embodiment includes logic to receive an identity indicator from a search logic. The identity indicator is associated with a search item that the search logic determines to be relevant to a search request. The example system may also include logic to determine whether the search result associated with the identity indicator is a duplicate result based on comparing the identity indicator to another identity indicator associated with another search result. | 09-11-2008 |
| 20090083201 | SYSTEM AND METHOD FOR DETERMINING STABILITY OF A NEURAL SYSTEM - Disclosed are methods, systems, and computer-readable media for determining stability of a neural system. The method includes tracking a function world line of an N element neural system within at least one behavioral space, determining whether the tracking function world line is approaching a psychological stability surface, and implementing a quantitative solution that corrects instability if the tracked function world line is approaching the psychological stability surface. | 03-26-2009 |
| 20090083202 | SEMICONDUCTOR STORAGE DEVICE - A semiconductor storage device includes a storage part including a plurality of nonvolatile semiconductor memory cells each having a conductive path, a charge storage layer and a control gate electrode. The device further includes a plurality of first input terminals each connected to one end of the conductive path of each nonvolatile semiconductor memory cell, a plurality of second input terminals each connected to the control gate of each nonvolatile semiconductor memory cell, and an output end connected to the other ends of the conductive paths of the plurality of nonvolatile semiconductor memory cells, respectively. | 03-26-2009 |
| 20090089229 | MOBILE BRAIN-BASED DEVICE HAVING A SIMULATED NERVOUS SYSTEM BASED ON THE HIPPOCAMPUS - A brain-based device (BBD) having a physical mobile device NOMAD controlling and under control by a simulated nervous system. The simulated nervous system is based on an intricate anatomy and physiology of the hippocampus and its surrounding neuronal regions including the cortex. The BBD integrates spatial signals from numerous objects in time and provides flexible navigation solutions to aid in the exploration of unknown environments. As NOMAD navigates in its real world environment, the hippocampus of the simulated nervous system organizes multi-modal input information received from sensors on NOMAD over timescales and uses this organization for the development of spatial and episodic memories necessary for navigation. | 04-02-2009 |
| 20090259605 | HIGH RESOLUTION MONITORING OF CD VARIATIONS - An optical metrology method is disclosed for evaluating the uniformity of characteristics within a semiconductor region having repeating features such a memory die. The method includes obtaining measurements with a probe laser beam having a spot size on the order of micron. These measurements are compared to calibration information obtained from calibration measurements. The calibration information is derived by measuring calibration samples with the probe laser beam and at least one other technology having added information content. In the preferred embodiment, the other technology includes at least one of spectroscopic reflectometry or spectroscopic ellipsometry. | 10-15-2009 |
| 20090327180 | STORAGE SYSTEM DYNAMIC CLASSIFICATION - The classification of data stored on a storage medium is dynamically modified without the data being relocated to another storage medium. Data stored on a plurality of storage mediums is classified independent of the physical location at which the data resides. Rather than moving data to storage media that possess different classifications, the data itself receives a classification apart from the storage medium. Data which is considered high priority would be afforded maximum use of the storage medium resources and bandwidth availability. Data that is of lower interest is classified with a lower classification resulting in differing levels of resources authorized to access that data. Throughout this reclassification process the data remains resident on the same storage medium. | 12-31-2009 |
| 20100036783 | Method of and apparatus for combining artificial intelligence (AI) concepts with event-driven security architectures and ideas - User authentication apparatus controlling access to systems, inputs owner's login name and password and then extracts the owner's timing vectors from keystroke characteristics with which the owner forms a training set. A semantic network uses multiple links to indicate that different pattern components of user's behavioral access create different kinds of relationships and “symbolic representations”. A neural network is trained by using each of the owner's timing vectors in the training set as an input. When a user inputs the owner's login name and password, it's checked and the user's timing vector is extracted to type the user's password if checked and demoted in confidence level if otherwise. The user's timing vector is applied to neural network and difference between the input/output is compared with a predetermined threshold; and if the difference is greater than the threshold, is prohibited. Preferably this is aided by response time to personal questions. | 02-11-2010 |
| 20100049679 | CROSS CHANNEL OPTIMIZATION SYSTEMS AND METHODS - The inventive subject matter is generally directed to a cross channel optimization system, methods, and related software which provide for the conducting of experiments and/or optimization of digital content across a plurality of external content systems to user of the external content systems. | 02-25-2010 |
| 20100070445 | SYSTEM, METHOD AND COMPUTER PROGRAM PRODUCT FOR REAL-TIME EVENT IDENTIFICATION AND COURSE OF ACTION INTERPRETATION - A system for identifying events includes a memory capable of storing a compressed event table including a number of events, the event table having been compressed by reducing the number of events in the event table without reducing the number of events represented by the event table. Each event of the event table includes a set of state parameters, and may also be associated with an output. The system also includes a processor capable of operating a fast state recognition (FSR) application. The FSR application, in turn, can receive a plurality of inputs, and identify an event of the compressed event table based upon the plurality of inputs and the state parameters of the compressed event table, event being identified in accordance with a state recognition technique. | 03-18-2010 |
| 20100088261 | Method and system for fully automated energy curtailment - Fully automated demand response may be implemented at end users, in accordance with terms agreed to by end users to reduce energy demand during demand response events. Demand reduction actions to implement the objectives of a demand response event at the end users may be determined, desirably using artificial intelligence and neural networks, based on energy demand curtailment objectives of the demand response event, hierarchy(ies) of demand reduction actions for respective demand response events ordered to minimize undesired impact at the end users, and monitoring data received from, or relating to implementing energy demand curtailment at, the end users. In addition, demand reduction actions may be automatically implemented at end users in the absence of a demand response event, to implement energy demand curtailment according to criteria of end users, where the demand reduction actions are determined based on monitoring data and a hierarchy(ies) of demand reduction actions and using artificial intelligence and neural networks. | 04-08-2010 |
| 20100131440 | EXPERIENCE TRANSFER FOR THE CONFIGURATION TUNING OF LARGE SCALE COMPUTING SYSTEMS - A computer implemented method employing experience transfer to improve the efficiencies of an exemplary configuration tuning in computing systems. The method employs a Bayesian network guided tuning algorithm to discover the optimal configuration setting. After the tuning has been completed, a Bayesian network is obtained that records the parameter dependencies in the original system. Such parameter dependency knowledge has been successfully embedded to accelerate the configuration searches in other systems. Experimental results have demonstrated that with the help of transferred experiences we can achieve significant time savings for the configuration tuning task. | 05-27-2010 |
| 20100306143 | EFFORT ESTIMATION USING TEXT ANALYSIS - A system, method and program product for estimating effort of implementing a system based on a use case specification document. A system is provided that includes: a volumetrics processor that quantifies a structure of the document and evaluates a format of the document; a domain processor that identifies a domain of the system associated with the document; a complexity processor that defines a set of complexity variables associated with the document based on the structure of the document, a format of the document and a domain of the document; and a neural network that estimates an effort based on the set of complexity variables. | 12-02-2010 |
| 20110016068 | CONSTANT MEMORY IMPLEMENTATION OF A PHASE-MODEL NEURAL NETWORK - Disclosed are systems, apparatuses, and methods for implementing a phase-model neural network using a fixed amount of memory. Such a phase-model neural network includes a plurality of neurons, wherein each neuron is associated with two parameters—an activity and a phase. Example methods include (i) generating a sequence of variables associated with a probability distribution of phases and (ii) sequentially sampling the probability distribution of phases using a fixed amount of memory, regardless of a number of phases used in the phase-model neural network. | 01-20-2011 |
| 20110055129 | Process and device for representation of a scanning function - The invention concerns a process for the representation of a scanning function by means of a neuronal network and a device for the implementation of the process, whereby measurement values associated with a turbulent wave front, which contain phase information, are compared with reference values, with the result that the intermediate values thus obtained can be compared with comparison functions, in order, in the best case, to describe the measured pattern with a selection of comparison functions, whereby a neuronal network is trained in the comparison functions, so that the processing of the measured pattern can take place in near-real time. | 03-03-2011 |
| 20110071968 | MOBILE BRAIN-BASED DEVICE HAVING A SIMULATED NERVOUS SYSTEM BASED ON THE HIPPOCAMPUS - A brain-based device (BBD) having a physical mobile device NOMAD controlling and under control by a simulated nervous system. The simulated nervous system is based on an intricate anatomy and physiology of the hippocampus and its surrounding neuronal regions including the cortex. The BBD integrates spatial signals from numerous objects in time and provides flexible navigation solutions to aid in the exploration of unknown environments. As NOMAD navigates in its real world environment, the hippocampus of the simulated nervous system organizes multi-modal input information received from sensors on NOMAD over timescales and uses this organization for the development of spatial and episodic memories necessary for navigation. | 03-24-2011 |
| 20110071969 | NEURO TYPE-2 FUZZY BASED METHOD FOR DECISION MAKING - According to a first aspect of the invention there is provided a method of decision-making comprising: a data input step to input data from a plurality of first data sources into a first data bank, analysing said input data by means of a first adaptive artificial neural network (ANN), the neural network including a plurality of layers having at least an input layer, one or more hidden layers and an output layer, each layer comprising a plurality of interconnected neurons, the number of hidden neurons utilised being adaptive, the ANN determining the most important input data and defining therefrom a second ANN, deriving from the second ANN a plurality of Type-1 fuzzy sets for each first data source representing the data source, combining the Type-1 fuzzy sets to create Footprint of Uncertainty (FOU) for type-2 fuzzy sets, modelling the group decision of the combined first data sources; inputting data from a second data source, and assigning an aggregate score thereto, comparing the assigned aggregate score with a fuzzy set representing the group decision, and producing a decision therefrom. A method employing a developed ANN as defined in Claim | 03-24-2011 |
| 20110289032 | 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. | 11-24-2011 |
| 20120041914 | System and Method for Effective Caching Using Neural Networks - Systems and methods for selecting an appropriate caching algorithm to be used when temporarily storing data accessed by an executing application using a neural network may dynamically and/or iteratively replace an initial caching algorithm being used for the application. An input layer of the neural network may gather values of performance related parameters, such as cache hit rates, data throughput rates, or memory access request response times. The neural network may detect a pattern or change in a pattern of accesses, or a change in a workload, a hardware component, or an operating system parameter. Dependent on these and/or other inputs, the neural network may select and apply a caching algorithm likely to improve performance of the application. Other inputs to the neural network may include values of hardware configuration parameters and/or operating system parameters. The neural network may perform a training exercise or may be self-training, e.g., using reinforcement learning. | 02-16-2012 |
| 20120158629 | DETECTING AND RESPONDING TO UNINTENTIONAL CONTACT WITH A COMPUTING DEVICE - A computing device is described herein for detecting and addressing unintended contact of a hand portion (such as a palm) or other article with a computing device. The computing device uses multiple factors to determine whether input events are accidental, including, for instance, the tilt of a pen device as it approaches a display surface of the computing device. The computing device can also capture and analyze input events which represent a hand that is close to the display surface, but not making physical contact with the display surface. The computing device can execute one or more behaviors to counteract the effect of any inadvertent input actions that it may detect. | 06-21-2012 |
| 20120173469 | EFFORT ESTIMATION USING TEXT ANALYSIS - A system, method and program product for estimating effort of implementing a system based on a use case specification document. A method is provided that includes: quantifying a structure of the document and evaluating a format of the document using a computing device; identifying a domain of an application associated with the document; defining a set of complexity variables associated with the document based on the structure of the document, a format of the document and a domain of the document; using a neural network to estimate an effort based on the set of complexity variables; and outputting the effort via a tangible medium. | 07-05-2012 |
| 20120173470 | PREDICTION AND PREVENTION OF POSTOPERATIVE ATRIAL FIBRILLATION IN CARDIAC SURGERY PATIENTS - Systems and methods are provided for predicting the onset of postoperative atrial fibrillation (AF) from electrocardiogram (ECG) data representing a patient. A signal processing component determines parameters representing the activity of the heart of the patient from the ECG data. A feature extraction component calculates a plurality of features useful in predicting postoperative AF from the determined parameters. A classification component determines an AF index for the patient from the calculated plurality of features. The AF index represents the likelihood that the patient will experience AF. | 07-05-2012 |
| 20120239602 | SOLVING THE DISTAL REWARD PROBLEM THROUGH LINKAGE OF STDP AND DOPAMINE SIGNALING - In Pavlovian and instrumental conditioning, rewards typically come seconds after reward-triggering actions, creating an explanatory conundrum known as the distal reward problem or the credit assignment problem. How does the brain know what firing patterns of what neurons are responsible for the reward if (1) the firing patterns are no longer there when the reward arrives and (2) most neurons and synapses are active during the waiting period to the reward? A model network and computer simulation of cortical spiking neurons with spike-timing-dependent plasticity (STDP) modulated by dopamine (DA) is disclosed to answer this question. STDP is triggered by nearly-coincident firing patterns of a presynaptic neuron and a postsynaptic neuron on a millisecond time scale, with slow kinetics of subsequent synaptic plasticity being sensitive to changes in the extracellular dopamine DA concentration during the critical period of a few seconds after the nearly-coincident firing patterns. | 09-20-2012 |
| 20120265719 | ELECTRONIC LEARNING SYNAPSE WITH SPIKE-TIMING DEPENDENT PLASTICITY USING MEMORY-SWITCHING ELEMENTS - A system, method and computer program product produce spike-dependent plasticity in an artificial synapse. A method includes: an electronic device generating a pre-synaptic pulse that occurs a predetermined period of time after receiving a pre-synaptic spike at a first input. The electronic device generating a post-synaptic pulse that starts at a baseline value and reaches a first voltage value a first period of time after receiving a post-synaptic spike at a second input, followed by a second voltage value a second period of time after the post synaptic spike, followed by a return to said baseline voltage a third period of time after the post-synaptic spike. The generated pre-synaptic pulse is applied to a pre-synaptic node of a synaptic device in series with a rectifying element that has a turn-on voltage based on a threshold. The generated post-synaptic pulse is applied to a post-synaptic node of said synaptic device. | 10-18-2012 |
| 20130073491 | APPARATUS AND METHODS FOR SYNAPTIC UPDATE IN A PULSE-CODED NETWORK - Apparatus and methods for efficient synaptic update in a network such as a spiking neural network. In one embodiment, the post-synaptic updates, in response to generation of a post-synaptic pulse by a post-synaptic unit, are delayed until a subsequent pre-synaptic pulse is received by the unit. Pre-synaptic updates are performed first following by the post-synaptic update, thus ensuring synaptic connection status is up-to-date. The delay update mechanism is used in conjunction with system “flush” events in order to ensure accurate network operation, and prevent loss of information under a variety of pre-synaptic and post-synaptic unit firing rates. A large network partition mechanism is used in one variant with network processing apparatus in order to enable processing of network signals in a limited functionality embedded hardware environment. | 03-21-2013 |
| 20130132314 | SYSTEMS AND METHODS FOR MODELING BINARY SYNAPSES - Methods and system for modeling the behavior of binary synapses are provided. In one aspect, a method of modeling synaptic behavior includes receiving an analog input signal and transforming the analog input signal into an N-bit codeword, wherein each bit of the N-bit codeword is represented by an electronic pulse ( | 05-23-2013 |
| 20130144821 | Digital-to-Analogue Converter and Neuromorphic Circuit Using Such a Converter - A digital-to-analogue converter, with application to electronic circuits with neuromorphic architecture, comprises: transistors of identical nominal geometrical characteristics, but of dispersed current-voltage characteristics, wherein when a constant gate-source voltage is applied to the different transistors, a current varying as a function of the dispersion circulates in the transistor; a digital table receiving a digital word and having a selection output selecting, as a function of the word to be converted, a transistor or transistors supplying a current of desired value representing this word in analogue form. The look-up table is loaded as a function of real measured current-voltage characteristics of different transistors of the set, to establish a look-up between words and current values. The wide variability of characteristics of the transistors, notably their leakage current for a gate-source voltage below the switch-on threshold, allows finding combinations of leakage currents which are a good representation of words to be converted. | 06-06-2013 |
| 20130268470 | SYSTEM AND METHOD FOR FILTERING SPAM MESSAGES BASED ON USER REPUTATION - System for updating filtering rules for messages received by a plurality of users including a filtering rules database storing filtering rules for the users; means for distributing the filtering rules to the users; a user reputation database comprising a reputation weight for each user; and means for receiving and processing of user reports that indicate that a message belongs to a particular category. The means for receiving (i) calculates a message weight in its category based on a number of reports received from multiple users and a reputation weights of those users, (ii) decides whether the message belongs to the particular category if the message weight exceeds a predefined threshold, (iii) updates the filtering rules in the filtering rules database based on the deciding, and (iv) distributes the updated filtering rules from the filtering rules database to the users using the means for distributing. | 10-10-2013 |
| 20130282633 | METHOD AND APPARATUS FOR DEFINING AN ARTIFICIAL BRAIN VIA A PLURALITY OF CONCEPT NODES - A method for defining a network of nodes is provided, each representing a unique concept, and making connections between individual concepts through unique relationships to other concepts. Each of the nodes is operable to store a unique identifier in the network and information regarding the concept in addition to the unique relationships. | 10-24-2013 |
| 20130304680 | PREDICTIVE CORROSION COUPONS FROM DATA MINING - In accordance with aspects of the present disclosure, a computer-implemented method for predicting a material deterioration of a coupon inserted into the well line system is disclosed. The computer-implemented method can be stored on a tangible and non-transitory computer readable medium and arranged to be executed by one or more processors that cause the one or more processors to receive data related to the well line system; determine one or more predictors of material deterioration of a coupon based on the data; and predict a material deterioration of the coupon inserted into the well line system based on a mathematical model of the material deterioration using the one or more predictors. | 11-14-2013 |
| 20130325765 | CONTINUOUS TIME SPIKING NEURAL NETWORK EVENT-BASED SIMULATION - Certain aspects of the present disclosure provide methods and apparatus for a continuous-time neural network event-based simulation that includes a multi-dimensional multi-schedule architecture with ordered and unordered schedules and accelerators to provide for faster event sorting; and a formulation of modeling event operations as anticipating (the future) and advancing (update/jump ahead/catch up) rules or methods to provide a continuous-time neural network model. In this manner, the advantages include faster simulation of spiking neural networks (order(s) of magnitude); and a method for describing and modeling continuous time neurons, synapses, and general neural network behaviors. | 12-05-2013 |
| 20130325766 | SPIKING NEURON NETWORK APPARATUS AND METHODS - Apparatus and methods for heterosynaptic plasticity in a spiking neural network having multiple neurons configured to process sensory input. In one exemplary approach, a heterosynaptic plasticity mechanism is configured to select alternate plasticity rules when performing neuronal updates. The selection mechanism is adapted based on recent post-synaptic activity of neighboring neurons. When neighbor activity is low, a regular STDP update rule is effectuated. When neighbor activity is high, an alternate STDP update rule, configured to reduce probability of post-synaptic spike generation by the neuron associated with the update, is used. The heterosynaptic mechanism impedes that neuron to respond to (or learn) features within the sensory input that have been detected by neighboring neurons, thereby forcing the neuron to learn a different feature or feature set. The heterosynaptic methodology advantageously introduces competition among neighboring neurons, in order to increase receptive field diversity and improve feature detection capabilities of the network. | 12-05-2013 |
| 20140006324 | AUTOMATIC EVENT ANALYSIS | 01-02-2014 |
| 20140074761 | DYNAMICAL EVENT NEURON AND SYNAPSE MODELS FOR LEARNING SPIKING NEURAL NETWORKS - Certain aspects of the present disclosure support a technique for updating the state of an artificial neuron. A first state of the artificial neuron can be first determined, wherein a neuron model for the artificial neuron has a closed-form solution in continuous time and wherein state dynamics of the neuron model are divided into two or more regimes. An operating regime for the artificial neuron can be determined based, at least in part, on the first state. The state of the artificial neuron can be updated based, at least in part, on the first state of the artificial neuron and the determined operating regime. | 03-13-2014 |
| 20140101084 | Methods, Systems, and Products for Interfacing with Neurological and Biological Networks - Methods, systems, and products provide interfaces between intrahost networks and interhost networks within biological hosts. Neuroregional translations are performed to route communications to and from the biological hosts. Bioregional translations may also be performed to route communications to and from the biological hosts. | 04-10-2014 |
| 20140122397 | ADAPTIVE PLASTICITY APPARATUS AND METHODS FOR SPIKING NEURON NETWORK - Apparatus and methods for plasticity in a spiking neuron network. In one implementation, a plasticity mechanism is configured based on a similarity measure between neuron post-synaptic and pre-synaptic activity. The similarity measure may comprise a cross-correlogram between the output spike train and input spike train, determined over a plasticity window. Several correlograms, corresponding to individual input connections delivering pre-synaptic input, may be combined. The combination may comprise for example a weighted average. The averaged correlograms may be used to construct the long term potentiation component of the plasticity. The long term depression component of the plasticity may comprise e.g., a monotonic function based on a statistical parameter associated with the adaptively determined long term potentiation component. | 05-01-2014 |
| 20140122398 | MODULATED PLASTICITY APPARATUS AND METHODS FOR SPIKING NEURON NETWORK - Apparatus and methods for modulated plasticity in a spiking neuron network. A plasticity mechanism may be configured for example based on a similarity measure between post-synaptic activities of two or more neurons that may be receiving the same feed-forward input. The similarity measure may comprise a dynamically determined cross-correlogram between the output spike trains of two neurons. An a priori configured similarity measure may be used during network operation in order to update efficacy of inhibitory connections between neighboring neurons. Correlated output activity may cause one neuron to inhibit output generation by another neuron thereby hindering responses by multiple neurons to the same input stimuli. The inhibition may be based on an increased efficacy of inhibitory lateral connection. The inhibition may comprise modulation of the pre synaptic portion the plasticity rule based on efficacies of feed-forward connection and inhibitory connections and a statistical parameter associated with the post-synaptic rule. | 05-01-2014 |
| 20140122399 | APPARATUS AND METHODS FOR ACTIVITY-BASED PLASTICITY IN A SPIKING NEURON NETWORK - Apparatus and methods for plasticity in spiking neuron network. The network may comprise feature-specific units capable of responding to different objects (red and green color). Plasticity mechanism may be configured based on difference between two similarity measures related to activity of different unit types obtained during network training. One similarity measure may be based on activity of units of the same type (red). Another similarity measure may be based on activity of units of one type (red) and another type (green). Similarity measures may comprise a cross-correlogram and/or mutual information determined over an activity window. Several similarity estimates, corresponding to different unit-to-unit pairs may be combined. The combination may comprise a weighted average. During network operation, the activity based plasticity mechanism may be used to potentiate connections between units of the same type (red-red). The plasticity mechanism may be used to depress connections between units of different types (red-green). | 05-01-2014 |
| 20140122400 | APPARATUS AND METHODS FOR ACTIVITY-BASED PLASTICITY IN A SPIKING NEURON NETWORK - Apparatus and methods for plasticity in spiking neuron network. The network may comprise feature-specific units capable of responding to different objects (red and green color). Plasticity mechanism may be configured based on difference between two similarity measures related to activity of different unit types obtained during network training. One similarity measure may be based on activity of units of the same type (red). Another similarity measure may be based on activity of units of one type (red) and another type (green). Similarity measures may comprise a cross-correlogram and/or mutual information determined over an activity window. Several similarity estimates, corresponding to different unit-to-unit pairs may be combined. The combination may comprise a weighted average. During network operation, the activity based plasticity mechanism may be used to potentiate connections between units of the same type (red-red). The plasticity mechanism may be used to depress connections between units of different types (red-green). | 05-01-2014 |
| 20140143190 | PIECEWISE LINEAR NEURON MODELING - Methods and apparatus for piecewise linear neuron modeling and implementing artificial neurons in an artificial nervous system based on linearized neuron models. One example method for operating an artificial neuron generally includes determining that a first state of the artificial neuron is within a first region; determining a second state of the artificial neuron based at least in part on a first set of linear equations, wherein the first set of linear equations is based at least in part on a first set of parameters corresponding to the first region; determining that the second state of the artificial neuron is within a second region; and determining a third state of the artificial neuron based at least in part on a second set of linear equations, wherein the second set of linear equations is based at least in part on a second set of parameters corresponding to the second region. | 05-22-2014 |
| 20140143191 | PIECEWISE LINEAR NEURON MODELING - Methods and apparatus for piecewise linear neuron modeling and implementing one or more artificial neurons in an artificial nervous system based on one or more linearized neuron models. One example method (for implementing a combination of a plurality of neuron models in a system of neural processing units) generally includes loading parameters for a first neuron model selected from the plurality of neuron models into a first neural processing unit, determining a first state of the first neural processing unit based at least in part on the parameters for the first neuron model, and determining a second state of the first neural processing unit based at least in part on the parameters for the first neuron model and on the first state. This method may also include updating the plurality of neuron models (e.g., by adding, deleting, or adjusting parameters for the first neuron model or another neuron model). | 05-22-2014 |
| 20140156574 | RATE STABILIZATION THROUGH PLASTICITY IN SPIKING NEURON NETWORK - Apparatus and methods for activity based plasticity in a spiking neuron network adapted to process sensory input. In one embodiment, the plasticity mechanism may be configured for example based on activity of one or more neurons providing feed-forward stimulus and activity of one or more neurons providing inhibitory feedback. When an inhibitory neuron generates an output, inhibitory connections may be potentiated. When an inhibitory neuron receives inhibitory input, the inhibitory connection may be depressed. When the inhibitory input arrives subsequent to the neuron response, the inhibitory connection may be depressed. When input features are unevenly distributed in occurrence, the plasticity mechanism is capable of reducing response rate of neurons that develop receptive fields to more prevalent features. Such functionality may provide network output such that rarely occurring features are not drowned out by more widespread stimulus. | 06-05-2014 |
| 20140180983 | Inferring Contextual User Status and Duration - In one embodiment, a method includes one or more server computing devices receiving first data associated with an activity recently performed or currently being performed by a user of one or more client computing devices. A current state of the user is inferred at least in part by analyzing at least the first data, and second data associated with one or more historical durations associated with the inferred current state is accessed. An end time associated with the inferred current state is estimated based at least in part on the second data. | 06-26-2014 |
| 20140180984 | TIME-DIVISION MULTIPLEXED NEUROSYNAPTIC MODULE WITH IMPLICIT MEMORY ADDRESSING FOR IMPLEMENTING A UNIVERSAL SUBSTRATE OF ADAPTATION - Embodiments of the invention relate to a time-division multiplexed neurosynaptic module with implicit memory addressing for implementing a universal substrate of adaptation. One embodiment comprises a neurosynaptic device including a memory device that maintains neuron attributes for multiple neurons. The module further includes multiple bit maps that maintain incoming firing events for different periods of delay and a multi-way processor. The processor includes a memory array that maintains a plurality of synaptic weights. The processor integrates incoming firing events in a time-division multiplexing manner. Incoming firing events are integrated based on the neuron attributes and the synaptic weights maintained. | 06-26-2014 |
| 20140258194 | GENERIC METHOD FOR DESIGNING SPIKE-TIMING DEPENDENT PLASTICITY (STDP) CURVES - Methods and apparatus are provided for designing spike-timing dependent plasticity (STDP) curves whose parameter values are based on a set of equations. One example method generally includes operating an artificial nervous system by determining a set of equations based at least in part on a form of an STDP function defined by one or more parameters, determining values of the parameters for the STDP function based at least in part on the set of equations, and operating at least a portion of the artificial nervous system according to the STDP function having the determined parameter values. | 09-11-2014 |
| 20140279770 | ARTIFICIAL NEURAL NETWORK INTERFACE AND METHODS OF TRAINING THE SAME FOR VARIOUS USE CASES - An Artificial Neural Network Interface (ANNI) is disclosed along with use cases for the same. The ANNI utilizes one or more decision trees and/or probabilistic/combinatoric analysis to determine optimal responses to current conditions. The ANNI is also enabled to learn new conditions that are accepted as normal and, in response thereto, update the decision tree(s). | 09-18-2014 |
| 20140310216 | METHOD FOR GENERATING COMPACT REPRESENTATIONS OF SPIKE TIMING-DEPENDENT PLASTICITY CURVES - A method generates compact representations of spike timing-dependent plasticity (STDP) curves. The method includes segmenting a set of data points into different sections. The method further includes representing at least one section as a primitive and storing parameters of the primitive. The primitive can be a polynomial. | 10-16-2014 |
| 20140310217 | DEFINING DYNAMICS OF MULTIPLE NEURONS - A method for dynamically setting a neuron value processes a data structure including a set of parameters for a neuron model and determines a number of segments defined in the set of parameters. The method also includes determining a number of neuron types defined in the set of parameters and determining at least one boundary for a first segment. | 10-16-2014 |
| 20140365413 | EFFICIENT IMPLEMENTATION OF NEURAL POPULATION DIVERSITY IN NEURAL SYSTEM - Certain aspects of the present disclosure support a technique for efficient implementation of neural population diversity in neural systems. A set of parameters for each class of artificial neurons of a plurality of classes can be stored in a storage medium. A generator can be configured to obtain noise parameters for each class of artificial neurons in the neural system. After that, the noise parameters can be combined with the set of parameters for each class of artificial neurons to obtain a dithered set of parameters for each class of artificial neurons. The dithered set of parameters can be stored for each class of artificial neurons to be used for a neuron model for the artificial neurons that emulates behavior of the artificial neurons in the neural system. | 12-11-2014 |
| 20140379623 | APPARATUS AND METHODS FOR PROCESSING INPUTS IN AN ARTIFICIAL NEURON NETWORK - Apparatus and methods for processing inputs by one or more neurons of a network. The neuron(s) may generate spikes based on receipt of multiple inputs. Latency of spike generation may be determined based on an input magnitude. Inputs may be scaled using for example a non-linear concave transform. Scaling may increase neuron sensitivity to lower magnitude inputs, thereby improving latency encoding of small amplitude inputs. The transformation function may be configured compatible with existing non-scaling neuron processes and used as a plug-in to existing neuron models. Use of input scaling may allow for an improved network operation and reduce task simulation time. | 12-25-2014 |
| 20140379624 | INCREASED DYNAMIC RANGE ARTIFICIAL NEURON NETWORK APPARATUS AND METHODS - Apparatus and methods for processing inputs by one or more neurons of a network. The neuron(s) may generate spikes based on receipt of multiple inputs. Latency of spike generation may be determined based on an input magnitude. Inputs may be scaled using for example a non-linear concave transform. Scaling may increase neuron sensitivity to lower magnitude inputs, thereby improving latency encoding of small amplitude inputs. The transformation function may be configured compatible with existing non-scaling neuron processes and used as a plug-in to existing neuron models. Use of input scaling may allow for an improved network operation and reduce task simulation time. | 12-25-2014 |
| 20150012471 | SYSTEM FOR USER PSYCHOSOCIAL PROFILING - A profiling unit is provided herein. The profiling unit comprises a statistical module that characterizes user activity data statistically; a normalization module that normalizes the statistical data related to each user with respect to user populations; and an analysis unit that analyzes a correspondence between normalized user study data and user archetypes, and also associates, for each user, the normalized statistical data with one of the user archetypes according to the analyzed correspondence. The correspondence analysis is carried out by applying a heuristic genetic algorithm on an artificial neural network that represents the relation between the normalized user study data and the user archetypes. | 01-08-2015 |
| 20150046381 | IMPLEMENTING DELAYS BETWEEN NEURONS IN AN ARTIFICIAL NERVOUS SYSTEM - Methods and apparatus are provided for implementing delays in an artificial nervous system. Synaptic and/or axonal delays between a post-synaptic artificial neuron and one or more pre-synaptic artificial neurons may be accounted for at the post-synaptic artificial neuron. One example method for managing delay between neurons in an artificial nervous system generally includes receiving, at a post-synaptic artificial neuron, input current values from one or more pre-synaptic artificial neurons; accounting for delays between the one or more pre-synaptic artificial neurons and the post-synaptic artificial neuron at the post-synaptic artificial neuron; and determining a state of the post-synaptic artificial neuron based at least in part on at least a portion of the input current values, according to the accounting. | 02-12-2015 |
| 20150081605 | APPARATUS AND METHOD FOR DETERMINING CARELESS DRIVING - An apparatus and a method for determining careless driving are provided and determine more reliable careless driving by generating normal driving patterns using driving performance data for a reference time at the beginning of driving. In addition, careless driving patterns greater than a predetermined number are detected using the normal driving pattern and a boundary between the normal driving and the careless driving is determined using a supervised learning method. The careless driving of the driver is then determined based on the determined boundary. | 03-19-2015 |
| 20150294218 | Quantitative assessment of biological impact using mechanistic network models - A method to score a causally consistent network is provided by transforming the network into a hypothesis subnetwork, called a “HYP” (if the nodes have associated measurements) or a “meta-HYP” (if the nodes are themselves HYPs), and then applying known HYP scoring methods (e.g. (NPA, GPI, or the like) based on measurements or scores associated with nodes in the subnetwork. A method also is described for creating a HYP or meta-HYP with weights associated with each downstream node from a causally inconsistent network using a computational technique such as sampling of spanning trees. A further aspect is a method to transform a meta-HYP (with or without weights associated with each downstream node) into a HYP using the weights associated with each downstream node (where the weights are based on the scoring algorithms intended at the meta-HYP and HYP levels). | 10-15-2015 |
| 20150324685 | ADAPTIVE CONFIGURATION OF A NEURAL NETWORK DEVICE - A first input is processed via a first configuration of a neural network to produce a first output. The first configuration defines attributes of the neural network, such as connections between neural elements of the neural network. If the neural network requires a context switch to process a second input, a second configuration is applied to the neural network to change the attributes, and the second input is processed via the second configuration of the neural network to produce a second output. | 11-12-2015 |
| 20150356401 | GENERATING REPRESENTATIONS OF INPUT SEQUENCES USING NEURAL NETWORKS - Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating representations of input sequences. One of the methods includes obtaining an input sequence, the input sequence comprising a plurality of inputs arranged according to an input order; processing the input sequence using a first long short term memory (LSTM) neural network to convert the input sequence into an alternative representation for the input sequence; and processing the alternative representation for the input sequence using a second LSTM neural network to generate a target sequence for the input sequence, the target sequence comprising a plurality of outputs arranged according to an output order. | 12-10-2015 |
| 20150363687 | MANAGING SOFTWARE BUNDLING USING AN ARTIFICIAL NEURAL NETWORK - An artificial neural network is used to manage software bundling. During a training phase, the artificial neural network is trained using previously bundled software components having known values for identification attributes and known software bundle asociations. Once trained, the artifical neural network can be used to identify the proper software bundles for newly discovered sofware components. In this process, a newly discovered software component having known values for the identification attributes is identified. An input vector is derived from the known values. The input vector is loaded into input neurons of the artificial neural network. A yielded output vector is then obtained from an output neuron of the artificial neural network. Based on the composition of the output vector, the software bundle associated with this newly discovered software component is determined. | 12-17-2015 |
| 20160054940 | COMBINING DATA BLOCKS IN A NON-VOLATILE, SOLID-STATE MEMORY - First and second data representation are stored in first and second blocks of a non-volatile, solid-state memory. The first and second blocks share series-connected bit lines. The first and second blocks are selected and other blocks of the non-volatile, solid-state memory that share the bit lines are deselected. The bit lines are read to determine a combination of the first and second data representations. The combination may include a union or an intersection. | 02-25-2016 |
| 20190147319 | DEVICE AND METHOD FOR PROCESSING CONVOLUTION OPERATION USING KERNEL | 05-16-2019 |
| 20190147323 | Activation Functions for Deep Neural Networks | 05-16-2019 |
| 20190147324 | Neural Network Architecture Using Convolution Engines | 05-16-2019 |
| 20190147325 | Neural Network Architecture Using Control Logic Determining Convolution Operation Sequence | 05-16-2019 |
| 20190147326 | Neural Network Architecture Using Single Plane Filters | 05-16-2019 |
| 20190147327 | Neural Network Architecture Using Convolution Engine Filter Weight Buffers | 05-16-2019 |
| 20190147336 | METHOD AND APPARATUS OF OPEN SET RECOGNITION AND A COMPUTER READABLE STORAGE MEDIUM | 05-16-2019 |
| 20220138502 | GRAPH NEURAL NETWORK TRAINING METHODS AND SYSTEMS - Methods, systems, and apparatus for training a graph neural network. An example method includes obtaining a complete graph; dividing the complete graph into a plurality of subgraphs; obtaining a training graph to participate in graph neural network training based on selecting at least one subgraph from the plurality of subgraphs; obtaining, based on the training graph, a node feature vector of each node in the training graph; obtaining a node fusion vector of each current node in the training graph; determining a loss function based on node labels and the node fusion vectors in the training graph; and iteratively training the graph neural network to update parameter values of the graph neural network based on optimizing the loss function. | 05-05-2022 |
| 20220138524 | TRAINING NEURAL NETWORKS BASED ON DUAL PIPELINE ARCHITECTURES - Embodiments of the present disclosure include systems and methods for training neural networks based on dual pipeline architectures. In some embodiments, a first set of compute elements are configured to implement a first set of layers of a first instance of a neural network. A second set of compute elements are configured to implement a second set of layers of the first instance of the neural network. The second set of compute elements are further configured to implement a first set of layers of a second instance of the neural network. The first set of compute elements are further configured to implement a second set of layers of the second instance of the neural network. The first set of layers of the first instance of the neural network and the first set of layers of the second instance of the neural network are each configured to receive training data. | 05-05-2022 |
| 20220138528 | DATA PROCESSING METHOD FOR NEURAL NETWORK ACCELERATOR, DEVICE AND STORAGE MEDIUM - A data processing method for a neural network accelerator, an electronic device and a storage medium are provided. The technical solution includes: obtaining data to be processed and an operation to be executed; obtaining a real-number full-connection operation corresponding to the operation to be executed; and performing the real-number full-connection operation on the data based on a real-number full-connection unit of the neural network accelerator to obtain a result of the operation to be executed for the data. | 05-05-2022 |
| 20220138562 | METHOD FOR CREATING AN ARTIFICIAL NEURAL NETWORK (ANN) WITH ID-SPLINE-BASED ACTIVATION FUNCTION - The present technical solution relates to the field of artificial intelligence, particularly a computer-implemented method for creating a trained instance of an artificial neural network (ANN), comprising the following steps:
| 05-05-2022 |
| 20220138569 | LEARNING APPARATUS, METHOD, AND STORAGE MEDIUM - According to one embodiment, a learning apparatus includes a processing circuit. The processing circuit acquires first sequence data representing transition of inference performance according to a training progress of a first model trained in accordance with a first training parameter value concerning a specific training condition. The processing circuit performs iterative learning of a second model in accordance with a second training parameter value concerning the specific training condition and changes the second training parameter value based on the inference performance of the second model and the first sequence data in a training process of the second model. | 05-05-2022 |
| 20220138573 | METHODS AND SYSTEMS FOR TRAINING CONVOLUTIONAL NEURAL NETWORKS - A computer implemented method and system for training a convolutional neural network is provided. The method includes receiving a captured image. Based on the captured image, a statistical noise model is generated. A convolutional neural network is trained based on the captured image and the statistical model. | 05-05-2022 |
| 20220138574 | METHOD OF TRAINING MODELS IN AI AND ELECTRONIC DEVICE - A method of training models in AI and an electronic device are disclosed, the electronic device is connected to other electronic devices and a controller, each electronic device is deployed with a single initial machine learning model and can obtain a prediction accuracy and weightings of neurons of the trained machine learning model. The controller determines new weightings from a plurality of the received weightings according to a preset rule and a plurality of received prediction accuracies. Each electronic device updates the weightings of neurons of the trained machine learning model to the new weightings. An electronic device is also disclosed. The method reduces a cost of training a machine learning model, utilizes network resources more efficiently, and improves an accuracy of the machine learning model. | 05-05-2022 |
| 20220138624 | TIME-SERIES DATA PROCESSING METHOD - An information processing device | 05-05-2022 |
