Class / Patent application number | Description | Number of patent applications / Date published |
382158000 | Network structures | 19 |
20100166298 | NEURAL NETWORK BASED PATTERN RECOGNIZER - An image-based pattern recognizer and a method and apparatus for making such a pattern recognizer are disclosed. By employing positional coding, the meaning of any feature present in an image can be defined implicitly in space. The pattern recognizer can be a neural network including a plurality of stages of observers. The observers are configured to cooperate to identify the presence of features in the input image and to recognize a pattern in the input image based on the features. Each of the observers includes a plurality of neurons. The input image includes a plurality of units, and each of the observers is configured to generate a separate output set that includes zero or more coordinates of such units. | 07-01-2010 |
20140193066 | CONTRAST ENHANCEMENT SPIKING NEURON NETWORK SENSORY PROCESSING APPARATUS AND METHODS - Apparatus and methods for contrast enhancement and feature identification. In one implementation, an image processing apparatus utilizes latency coding and a spiking neuron network to encode image brightness into spike latency. The spike latency is compared to a saliency window in order to detect early responding neurons. Salient features of the image are associated with the early responding neurons. A inhibitory neuron receives salient feature indication and provides inhibitory signal to the other neurons within an area of influence of the inhibitory neuron. The inhibition signal reduces probability of responses by the other neurons to stimulus that is proximate to the feature thereby increasing contrast within the encoded data. The contrast enhancement may facilitate feature identification within the image. Feature detection may be used for example for image compression, background removal and content distribution. | 07-10-2014 |
20140369596 | CORRELATING VIDEOS AND SENTENCES - A method of testing a video against an aggregate query includes automatically receiving an aggregate query defining participant(s) and condition(s) on the participant(s). Candidate object(s) are detected in the frames of the video. A first lattice is constructed for each participant, the first-lattice nodes corresponding to the candidate object(s). A second lattice is constructed for each condition. An aggregate lattice is constructed using the respective first lattice(s) and the respective second lattice(s). Each aggregate-lattice node includes a scoring factor combining a first-lattice node factor and a second-lattice node factor. respective aggregate score(s) are determined of one or more path(s) through the aggregate lattice, each path including a respective plurality of the nodes in the aggregate lattice, to determine whether the video corresponds to the aggregate query. A method of providing a description of a video is also described and includes generating a candidate description with participant(s) and condition(s) selected from a linguistic model; constructing component lattices for the participant(s) or condition(s), producing an aggregate lattice having nodes combining component-lattice factors, and determining a score for the video with respect to the candidate description by determining an aggregate score for a path through the aggregate lattice. If the aggregate score does not satisfy a termination condition, participant(s) or condition(s) from the linguistic model are added to the condition, and the process is repeated. A method of testing a video against an aggregate query by mathematically optimizing a unified cost function is also described. | 12-18-2014 |
20150049938 | VISUAL CORTICAL CIRCUIT APPARATUS, VISUAL CORTICAL IMITATION SYSTEM AND OBJECT SEARCH SYSTEM USING VISUAL CORTICAL CIRCUIT APPARATUS - Provided us a visual cortical circuit apparatus comprising: a current mirror unit which uses a transistor as a current source to generate a current having the same size as that of a reaction; a transconductance unit which takes, as an input, the current generated by the current mirror unit and outputs a voltage using a transconductance; and a buffer unit for converting the voltage output from the transconductance unit into a current and buffering the current. | 02-19-2015 |
20150310303 | EXTRACTING SALIENT FEATURES FROM VIDEO USING A NEUROSYNAPTIC SYSTEM - Embodiments of the invention provide a method of visual saliency estimation comprising receiving an input sequence of image frames. Each image frame has one or more channels, and each channel has one or more pixels. The method further comprises, for each channel of each image frame, generating corresponding neural spiking data based on a pixel intensity of each pixel of the channel, generating a corresponding multi-scale data structure based on the corresponding neural spiking data, and extracting a corresponding map of features from the corresponding multi-scale data structure. The multi-scale data structure comprises one or more data layers, wherein each data layer represents a spike representation of pixel intensities of a channel at a corresponding scale. The method further comprises encoding each map of features extracted as neural spikes. | 10-29-2015 |
20150310311 | DYNAMICALLY RECONSTRUCTABLE MULTISTAGE PARALLEL SINGLE INSTRUCTION MULTIPLE DATA ARRAY PROCESSING SYSTEM - The present invention proposes a dynamically reconfigurable multistage parallel single instruction multiple data array processing system which has a pixel level parallel image processing element array and a row processor array parallel. The PE array mainly implements a linear operation which is adapted to be executed in parallel in the low and middle levels of image processing and the RP array implements an operation which is adapted to be executed in row-parallel in the low and middle levels of image processing or more complex nonlinear operations. In particularly, such a system may dynamically reconfigure a SOM neural network in a low cost of performance and area, and the neural network supports high level of image processing such as a high speed online neural network training and image feature recognition, and completely overcomes a defect in which a high level of image processing can't be done by pixel-level parallel processing array in the existing programmable vision chip and parallel vision processor, and facilitate an intelligent and portable real time on-chip vision image system with a complete function at low device cost and low power consumption. | 10-29-2015 |
20150339571 | SYSTEM AND METHOD FOR PARALLELIZING CONVOLUTIONAL NEURAL NETWORKS - A parallel convolutional neural network is provided. The CNN is implemented by a plurality of convolutional neural networks each on a respective processing node. Each CNN has a plurality of layers. A subset of the layers are interconnected between processing nodes such that activations are fed forward across nodes. The remaining subset is not so interconnected. | 11-26-2015 |
20150379689 | LENS DISTORTION CORRECTION USING A NEUROSYNAPTIC SYSTEM - Embodiments of the invention provide a system and circuit for image distortion correction. The system includes neurosynaptic core circuits that: receive a set of inputs comprising image dimensions and pixel distortion coefficients for one or more image frames via one or more input core circuits, map each distorted pixel to zero or more undistorted pixels by processing the set of inputs corresponding to each pixel of the one or more image frames by the one or more input core circuits, and route corresponding pixel intensity values of each distorted pixel to output undistorted pixels for each image frame via one or more output core circuits. | 12-31-2015 |
20160004931 | EXTRACTING SALIENT FEATURES FROM VIDEO USING A NEUROSYNAPTIC SYSTEM - Embodiments of the invention provide a method of visual saliency estimation comprising receiving an input sequence of image frames. Each image frame has one or more channels, and each channel has one or more pixels. The method further comprises, for each channel of each image frame, generating corresponding neural spiking data based on a pixel intensity of each pixel of the channel, generating a corresponding multi-scale data structure based on the corresponding neural spiking data, and extracting a corresponding map of features from the corresponding multi-scale data structure. The multi-scale data structure comprises one or more data layers, wherein each data layer represents a spike representation of pixel intensities of a channel at a corresponding scale. The method further comprises encoding each map of features extracted as neural spikes. | 01-07-2016 |
20160063359 | PROCESSING IMAGES USING DEEP NEURAL NETWORKS - Methods, systems, and apparatus, including computer programs encoded on computer storage media, for image processing using deep neural networks. One of the methods includes receiving data characterizing an input image; processing the data characterizing the input image using a deep neural network to generate an alternative representation of the input image, wherein the deep neural network comprises a plurality of subnetworks, wherein the subnetworks are arranged in a sequence from lowest to highest, and wherein processing the data characterizing the input image using the deep neural network comprises processing the data through each of the subnetworks in the sequence; and processing the alternative representation of the input image through an output layer to generate an output from the input image. | 03-03-2016 |
20160104056 | SPATIAL PYRAMID POOLING NETWORKS FOR IMAGE PROCESSING - Spatial pyramid pooling (SPP) layers are combined with convolutional layers and partition an input image into divisions from finer to coarser levels, and aggregate local features in the divisions. A fixed-length output may be generated by the SPP layer(s) regardless of the input size. The multi-level spatial bins used by the SPP layer(s) may provide robustness to object deformations. An SPP layer based system may pool features extracted at variable scales due to the flexibility of input scales making it possible to generate a full-image representation for testing. Moreover, SPP networks may enable feeding of images with varying sizes or scales during training, which may increase scale-invariance and reduce the risk of over-fitting. | 04-14-2016 |
20160140435 | GENERATING NATURAL LANGUAGE DESCRIPTIONS OF IMAGES - Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating descriptions of input images. One of the methods includes obtaining an input image; processing the input image using a first neural network to generate an alternative representation for the input image; and processing the alternative representation for the input image using a second neural network to generate a sequence of a plurality of words in a target natural language that describes the input image. | 05-19-2016 |
20160148078 | Convolutional Neural Network Using a Binarized Convolution Layer - A convolutional neural network is trained to analyze input data in various different manners. The convolutional neural network includes multiple layers, one of which is a convolution layer that performs a convolution, for each of one or more filters in the convolution layer, of the filter over the input data. The convolution includes generation of an inner product based on the filter and the input data. Both the filter of the convolution layer and the input data are binarized, allowing the inner product to be computed using particular operations that are typically faster than multiplication of floating point values. The possible results for the convolution layer can optionally be pre-computed and stored in a look-up table. Thus, during operation of the convolutional neural network, rather than performing the convolution on the input data, the pre-computed result can be obtained from the look-up table | 05-26-2016 |
20160189009 | SYSTEMS AND METHODS FOR DETERMINING VIDEO FEATURE DESCRIPTORS BASED ON CONVOLUTIONAL NEURAL NETWORKS - Systems, methods, and non-transitory computer-readable media can acquire video content for which video feature descriptors are to be determined. The video content can be processed based at least in part on a convolutional neural network including a set of two-dimensional convolutional layers and a set of three-dimensional convolutional layers. One or more outputs can be generated from the convolutional neural network. A plurality of video feature descriptors for the video content can be determined based at least in part on the one or more outputs from the convolutional neural network. | 06-30-2016 |
20160196480 | SYSTEMS AND METHODS FOR APPLYING A CONVOLUTIONAL NETWORK TO SPATIAL DATA | 07-07-2016 |
20160379092 | SYSTEM FOR BUILDING A MAP AND SUBSEQUENT LOCALIZATION - SLAM systems are provided that utilize an artificial neural network to both map environments and locate positions within the environments. In some example embodiments, a sensor arrangement is used to map an environment. The sensor arrangement acquires sensor data from the various sensors and associates the sensor data, or data derived from the sensor data, with spatial regions in the environment. The sensor data may include image data and inertial measurement data that effectively describes the visual appearance of a spatial region at a particular location and orientation. This diverse sensor data may be fused into camera poses. The map of the environment includes camera poses organized by spatial region within the environment. Further, in these examples, an artificial neural network is adapted to the features of the environment by a transfer learning process using image data associated with camera poses. | 12-29-2016 |
20170236027 | INTELLIGENT BIOMORPHIC SYSTEM FOR PATTERN RECOGNITION WITH AUTONOMOUS VISUAL FEATURE EXTRACTION | 08-17-2017 |
20180025249 | Object Detection System and Object Detection Method | 01-25-2018 |
20220139098 | IDENTIFICATION OF BLOCKS OF ASSOCIATED WORDS IN DOCUMENTS WITH COMPLEX STRUCTURES - Aspects of the disclosure provide for mechanisms for identification of blocks of associated words in documents using neural networks. A method of the disclosure includes obtaining a plurality of words of a document, the document having a first block of associated words, determining a plurality of vectors representative of the plurality of words, processing the plurality of vectors using a first neural network to obtain a plurality of recalculated vectors having values based on the plurality of vectors, determining a plurality of association values corresponding to a connections between at least two words of the document, and identifying, using the plurality of recalculated vectors and the plurality of association values, the first block of associated symbol sequences. | 05-05-2022 |