REDES NEURONALES

VolverVolver

Resultados 271 resultados LastUpdate Última actualización 11/07/2020 [20:05:00] pdf PDF xls XLS

Solicitudes publicadas en los últimos 60 días / Applications published in the last 60 days



Página1 de 11 nextPage   por página


IMAGE PROCESSING METHOD, IMAGE PROCESSING APPARATUS, AND A NEURAL NETWORK TRAINING METHOD

NºPublicación: EP3678059A1 08/07/2020

Solicitante:

BOE TECHNOLOGY GROUP CO LTD [CN]

US_2019220746_A1

Resumen de: EP3678059A1

A neural network training method, an image processing method, and an image processing apparatus for implementing image style transfer. The training method comprises: obtaining a first training input image and a second training input image (S10); inputting the first training input image to a neural network (S20); using the neural network to perform style transfer processing on the first training input image to obtain a training output image (S30); calculating a loss value of a parameter of the neural network by means of a loss function on the basis of the first training input image, the second training input image, and the training output image (S40); modifying the parameter of the neural network according to the loss value (S50); and when the loss value satisfies a preset condition, obtaining a trained neural network (S70), and when the loos value does not satisfy the preset condition, continuing to input the first training input image and the second training input image to repeat the training process above, wherein the loss function comprises a weight-to-bias ratio loss function.

traducir

AGILE VIDEO QUERY USING ENSEMBLES OF DEEP NEURAL NETWORKS

NºPublicación: US2020210780A1 02/07/2020

Solicitante:

PALO ALTO RES CT INC [US]

EP_3674924_A1

Resumen de: US2020210780A1

A method includes receiving a user object specified by a user. A similarity score is computed using a similarity function between the user object and one or more candidate objects in a database based on respective feature vectors. A first subset of the one or more candidate objects is presented to the user based on the respective computed similarity scores. First feedback is received from the user about the first subset of candidate objects. The similarity function is adjusted based on the received first feedback.

traducir

OUTPUT METHOD AND APPARATUS FOR MULTIPLE NEURAL NETWORK, SERVER AND COMPUTER READABLE STORAGE MEDIUM

NºPublicación: US2020210815A1 02/07/2020

Solicitante:

BAIDU ONLINE NETWORK TECHNOLOGY BEIJING CO LTD [CN]

EP_3674990_A1

Resumen de: US2020210815A1

The present disclosure provides an output method for multiple neural networks. The method includes dividing an operator operation process for each of the neural networks or operator operation processes for part of the neural networks into multiple times of executions according to a preset ratio of output frame rates among the multiple neural networks; and executing the operator operation processes for the multiple neural networks sequentially by switching among the networks, such that the multiple neural networks output uniformly and satisfy the preset ratio of output frame rates.

traducir

SET OF NEURAL NETWORKS

NºPublicación: US2020210814A1 02/07/2020

Solicitante:

DASSAULT SYSTEMES [FR]

EP_3674984_A1

Resumen de: US2020210814A1

The disclosure notably relates to a computer-implemented method of machine-learning. The method includes obtaining a dataset including 3D modeled objects which each represent a respective mechanical part and further includes providing a set of neural networks. Each neural network has respective weights. Each neural network is configured for inference of 3D modeled objects. The method further includes modifying respective weights of the neural networks by minimizing a loss. For each 3D modeled object, the loss selects a term among a plurality of terms. Each term penalizes a disparity between the 3D modeled object and a respective 3D modeled object inferred by a respective neural network of the set. The selected term is a term among the plurality of terms for which the disparity is the least penalized. This constitutes an improved method of machine-learning with a dataset including 3D modeled objects which each represent a respective mechanical part.

traducir

NEURAL NETWORK FOR IMAGE MULTI-LABEL IDENTIFICATION, RELATED METHOD, MEDIUM AND DEVICE

NºPublicación: US2020210773A1 02/07/2020

Solicitante:

BOE TECHNOLOGY GROUP CO LTD [CN]

CN_109711481_A

Resumen de: US2020210773A1

A neural network includes: a convolutional network; a multi-feature-layer merging network configured to merge feature maps output by a high-order convolutional layer and a low-order convolutional layer; a spatial regularization network configured to receive the merged feature map; a first content label full connection layer configured to receive a feature map and output a first prediction probability of a content label; a second content label full connection layer configured to receive an N-th order feature map and output a second prediction probability of the content label, the first prediction probability and the second prediction probability of the content label are summed and averaged to obtain a prediction probability; a theme label full connection layer configured to receive the N-th order feature map and output a prediction probability; and a category label full connection layer configured to output a prediction probability of a category label, where 1 traducir

ADJUSTING PRECISION AND TOPOLOGY PARAMETERS FOR NEURAL NETWORK TRAINING BASED ON A PERFORMANCE METRIC

NºPublicación: US2020210840A1 02/07/2020

Solicitante:

MICROSOFT TECHNOLOGY LICENSING LLC [US]

Resumen de: US2020210840A1

Apparatus and methods for training neural networks based on a performance metric, including adjusting numerical precision and topology as training progresses are disclosed. In some examples, block floating-point formats having relatively lower accuracy are used during early stages of training. Accuracy of the floating-point format can be increased as training progresses based on a determined performance metric. In some examples, values for the neural network are transformed to normal precision floating-point formats. The performance metric can be determined based on entropy of values for the neural network, accuracy of the neural network, or by other suitable techniques. Accelerator hardware can be used to implement certain implementations, including hardware having direct support for block floating-point formats.

traducir

METHOD AND SYSTEM OF ANNOTATION DENSIFICATION FOR SEMANTIC SEGMENTATION

NºPublicación: US2020211200A1 02/07/2020

Solicitante:

DIDI RES AMERICA LLC [US]

Resumen de: US2020211200A1

Methods and systems of annotation densification for semantic segmentation are disclosed herein. In one example embodiment, such a method includes obtaining image information, obtaining coarse annotation information, performing an image matting operation based upon the image information and based at least indirectly upon the coarse annotation information, and applying an already-trained Convolutional Neural Network (ConvNet) semantic segmentation model in relation to the image information. The method also includes performing a merging operation with respect to both first intermediate information generated at least indirectly by the performing of the image matting operation and second intermediate information generated at least indirectly by the applying of the ConvNet model, where the performing of the merging operation results in fine semantic segmentation annotation information, whereby an additional semantic segmentation model can be trained using that annotation information and the trained additional semantic segmentation model can be applied to generate semantic segmentation output information.

traducir

DISTANCE TO OBSTACLE DETECTION IN AUTONOMOUS MACHINE APPLICATIONS

NºPublicación: US2020210726A1 02/07/2020

Solicitante:

NVIDIA CORP [US]

Resumen de: US2020210726A1

In various examples, a deep neural network (DNN) is trained to accurately predict, in deployment, distances to objects and obstacles using image data alone. The DNN may be trained with ground truth data that is generated and encoded using sensor data from any number of depth predicting sensors, such as, without limitation, RADAR sensors, LIDAR sensors, and/or SONAR sensors. Camera adaptation algorithms may be used in various embodiments to adapt the DNN for use with image data generated by cameras with varying parameters—such as varying fields of view. In some examples, a post-processing safety bounds operation may be executed on the predictions of the DNN to ensure that the predictions fall within a safety-permissible range.

traducir

PATTERN RECOGNITION APPARATUS, PATTERN RECOGNITION METHOD, AND STORAGE MEDIUM

NºPublicación: US2020211567A1 02/07/2020

Solicitante:

NEC CORP [JP]

WO_2019053898_A1

Resumen de: US2020211567A1

Provided is a pattern recognition apparatus to provide classification robustness to any kind of domain variability. The pattern recognition apparatus 500 based on Neural Network (NN) includes: NN training unit 501 that trains an NN model to generate NN parameters, based on at least one first feature vector and at least one domain vector indicating one of subsets in a specific domain, wherein, the first feature vector is extracted from each of the subsets, the domain vector indicates an identifier corresponding to the each of the subsets; and NN verification unit 502 that verifies a pair of second feature vectors in the specific domain to output whether the pair indicates same individual or not, based on a target domain vector and the NN parameters.

traducir

JOINT OPTIMIZATION OF ENSEMBLES IN DEEP LEARNING

NºPublicación: US2020210812A1 02/07/2020

Solicitante:

D5AI LLC [US]

WO_2019067542_PA

Resumen de: US2020210812A1

Computer-implemented, machine-learning systems and methods relate to a combination of neural networks. The systems and methods train the respective member networks both (i) to be diverse and yet (ii) according to a common, overall objective. Each member network is trained or retrained jointly with all the other member networks, including member networks that may not have been present in the ensemble when a member is first trained.

traducir

METHODS AND SYSTEMS FOR GENERATING TRAINING DATA FOR NEURAL NETWORK

NºPublicación: US2020210778A1 02/07/2020

Solicitante:

YANDEX TAXI LLC [RU]

EP_3674972_A1

Resumen de: US2020210778A1

A method and device for generating training data for re-training an object detecting Neural Network (ODNN) are disclosed. The method includes inputting a first image into the ODNN configured to detect an object on the first image by determining a first portion of that image that corresponds to the object. The method includes inputting a second image into the ODNN configured to detect the object on the second image by determining a second portion of that image that corresponds to the object. The method includes comparing the first portion with the second portion to determine a detection similarity value. In response to this value being below a pre-determined threshold, the method includes using at least one of the first and second image for obtaining a human-assessed label. The method includes re-training the ODNN based on the at least one of the first and second image and the human-assessed label.

traducir

DATA PROCESSING METHOD BASED ON NEURAL NETWORK, TRAINING METHOD OF NEURAL NETWORK, AND APPARATUSES THEREOF

NºPublicación: US2020210811A1 02/07/2020

Solicitante:

SAMSUNG ELECTRONICS CO LTD [KR]

Resumen de: US2020210811A1

Provided is a method of processing data based on a neural network, the method including receiving input data; determining a hyper parameter of a first neural network that affects at least one of a speed of the first neural network and an accuracy of the first neural network by processing the input data based on a second neural network; and processing the input data based on the hyper parameter and the first neural network.

traducir

SEMANTIC SEGMENTATION USING DRIVER ATTENTION INFORMATION

NºPublicación: US2020210765A1 02/07/2020

Solicitante:

BOSCH GMBH ROBERT [DE]

Resumen de: US2020210765A1

Methods of creating trained semantic segmentation network models and operating vehicles using the model. One example method includes an outside view camera configured to capture images that represent an artificial representation of the driver's view, a driver-facing camera configured to capture a driver's eye movements, and an electronic controller. The electronic controller is configured to receive images from the cameras; calibrate the image of the driver's eye movement with the artificial driver view; create a pixel weighted heat map of the calibrated images; create a trained semantic segmentation neural network model and a trained attention neural network model using the pixel weighted heat map and the artificial driver view; and operate the vehicle using the trained semantic segmentation neural network model and the trained attention neural network model.

traducir

DEPLOYMENT OF DEEP NEURAL NETWORKS (DNN) IN EMBEDDED DEVICES BY MEANS OF PEER-TO-PEER ROUTING BETWEEN COMPUTATIONAL POINTS

NºPublicación: US2020210834A1 02/07/2020

Solicitante:

DATALOGIC IP TECH SRL [IT]

Resumen de: US2020210834A1

A system and method of executing a deep neural network (DNN) in a local area network (LAN) may include executing a partitioned deep neural network in multiple computational nodes (CPs) in devices operating on the LAN. An image frame may be captured by a device. The image frame may be processed by a first layer of the partitioned neural network by a CP operating on the device. In response to the device that captured the image frame determining to request processing assistance from another CP, a request using a peer-to-peer protocol to other CPs on the LAN may be performed. A feature map may be communicated to another CP selected using the peer-to-peer protocol to process the feature map by a next layer of the DNN.

traducir

SYSTEM AND METHOD FOR ADAPTING A NEURAL NETWORK MODEL ON A HARDWARE PLATFORM

NºPublicación: US2020210832A1 02/07/2020

Solicitante:

TESLA INC [US]

Resumen de: US2020210832A1

Systems and methods for adapting a neural network model on a hardware platform. An example method includes obtaining neural network model information comprising decision points associated with a neural network, with one or more first decision points being associated with a layout of the neural network. Platform information associated with a hardware platform for which the neural network model information is to be adapted is accessed. Constraints associated with adapting the neural network model information to the hardware platform are determined based on the platform information, with a first constraint being associated with a processing resource of the hardware platform and with a second constraint being associated with a performance metric. A candidate configuration for the neural network is generated via execution of a satisfiability solver based on the constraints, with the candidate configuration assigns values to the plurality of decision points.

traducir

METHODS AND APPARATUS FOR SIMILAR DATA REUSE IN DATAFLOW PROCESSING SYSTEMS

NºPublicación: US2020210759A1 02/07/2020

Solicitante:

NANJING LLUVATAR COREX TECH CO LTD DBA LLUVATAR COREX INC NANJING [CN]
NANJING ILUVATAR COREX TECH CO LTD DBA ILUVATAR COREX INC NANJING [CN]

Resumen de: US2020210759A1

A computerized method identifies an input and kernel similarity in binarized neural network (BNN) across different applications as they are being processed by processors such as a GPU. The input and kernel similarity in BNN across different applications are analyzed to reduce computation redundancy to accelerate BNN inference. A computer-executable instructions stored thereon an on-chip arrangement receives a first data value for a data source for processing by the BNN at an inference phase. The computer-executable instructions further receives a second data value for the data source for processing by the BNN at the inference phase. The first data value is processed bitwise operations. A difference between the first data value and the second data value is calculated. The difference is stored in the on-chip arrangement. The computer-executable instructions applies the bitwise operations to the stored difference.

traducir

AUGMENTING NEURAL NETWORKS

NºPublicación: US2020210851A1 02/07/2020

Solicitante:

GOOGLE LLC [US]

CN_111133458_A

Resumen de: US2020210851A1

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for augmenting a neural network with additional operations. One of the methods includes maintaining, by a computational graph system that manages execution of computational graphs representing neural network operations for users of the computational graph system, data specifying a plurality of pre-trained neural networks, wherein each of the pre-trained neural networks is a neural network that has been trained on training data to determine trained values of the respective parameters of the neural network; obtaining data specifying a user computational graph representing neural network operations, the user computational graph comprising a plurality of nodes connected by edges; identifying (i) an insertion point after a first node in the user computational graph and (ii) a particular pre-trained neural network from the plurality of pre-trained neural networks; and inserting a remote call node into the user computational graph.

traducir

LEARNING A NEURAL NETWORK FOR INFERENCE OF SOLID CAD FEATURES

NºPublicación: US2020210845A1 02/07/2020

Solicitante:

DASSAULT SYSTEMES [FR]

EP_3675062_A1

Resumen de: US2020210845A1

The disclosure notably relates to computer-implemented method for learning a neural network configured for inference, from a freehand drawing representing a 3D shape, of a solid CAD feature representing the 3D shape. The method includes providing a dataset including freehand drawings each representing a respective 3D shape, and learning the neural network based on the dataset. The method forms an improved solution for inference, from a freehand drawing representing a 3D shape, of a 3D modeled object representing the 3D shape.

traducir

Method for Identifying an Object Instance and/or Orientation of an Object

NºPublicación: US2020211220A1 02/07/2020

Solicitante:

SIEMENS AG [DE]

CN_111149108_A

Resumen de: US2020211220A1

Various embodiments of the teachings herein may include a method for identifying an object instance and determining an orientation of localized objects in noisy environments using an artificial neural network may include: recording a plurality of images of an object for obtaining a multiplicity of samples containing image data, object identity, and orientation; generating a training set and a template set from the samples; training the artificial neural network using the training set and a loss function; and determining the object instance and/or the orientation of the object by evaluating the template set using the artificial neural network. The loss function includes a dynamic margin.

traducir

NEURAL NETWORK ACTIVATION COMPRESSION WITH NARROW BLOCK FLOATING-POINT

NºPublicación: US2020210838A1 02/07/2020

Solicitante:

MICROSOFT TECHNOLOGY LICENSING LLC [US]

Resumen de: US2020210838A1

Apparatus and methods for training a neural network accelerator using quantized precision data formats are disclosed, and in particular for storing activation values from a neural network in a compressed format for use during forward and backward propagation training of the neural network. In certain examples of the disclosed technology, a computing system includes processors, memory, and a compressor in communication with the memory. The computing system is configured to perform forward propagation for a layer of a neural network to produced first activation values in a first block floating-point format. In some examples, activation values generated by forward propagation are converted by the compressor to a second block floating-point format having a narrower numerical precision than the first block floating-point format. The compressed activation values are stored in the memory, where they can be retrieved for use during back propagation.

traducir

FUSING OUTPUT OF ARTIFICIAL INTELLIGENCE NETWORKS

NºPublicación: US2020210810A1 02/07/2020

Solicitante:

AEROSPACE CORP [US]

Resumen de: US2020210810A1

Fusion of trained artificial intelligence (AI) neural networks to produce more accurate classifications is disclosed. Concatenation from each network being merged may be performed. The new set of features, which includes the concatenated layers, is then fed through a new classifier to form a single final classifier that uses the best parts of each input classifier.

traducir

NEURAL NETWORKS AND SYSTEMS FOR DECODING ENCODED DATA

NºPublicación: US2020210816A1 02/07/2020

Solicitante:

MICRON TECHNOLOGY INC [US]

Resumen de: US2020210816A1

Examples described herein utilize multi-layer neural networks to decode encoded data (e.g., data encoded using one or more encoding techniques). The neural networks may have nonlinear mapping and distributed processing capabilities which may be advantageous in many systems employing the neural network decoders. In this manner, neural networks described herein may be used to implement error code correction (ECC) decoders.

traducir

ENROLLMENT-FREE OFFLINE DEVICE PERSONALIZATION

NºPublicación: US2020210035A1 02/07/2020

Solicitante:

SYNAPTICS INC [US]

Resumen de: US2020210035A1

A method and apparatus for device personalization. A device is configured to receive first sensor data from one or more sensors, detect biometric information in the first sensor data, encode the biometric information as a first vector using one or more neural network models stored on the device, and configure a user interface of the device based at least in part on the first vector. For example, the profile information may include configurations, settings, preferences, or content to be displayed or rendered via the user interface. In some implementations, the first sensor data may comprise an image of a scene and the biometric information may comprise one or more facial features of a user in the scene.

traducir

IMAGE DATA PROCESSING SYSTEM AND METHOD

NºPublicación: US2020210688A1 02/07/2020

Solicitante:

HU MAN REN GONG ZHI NENG KE JI SHANGHAI LTD [CN]

CN_111183455_A

Resumen de: US2020210688A1

A method of recognising human characteristics from image data of a subject. The method comprises extracting a sequence of images of the subject from the image data; from each image estimating an emotion feature metric and a facial mid-level feature metric for the subject; for each image, combining the associated estimated emotion metric and estimated facial mid-level feature metric to form a feature vector, thereby forming a sequence of feature vectors, each feature vector associated with an image of the sequence of images, and inputting the sequence of feature vectors to a human characteristic recognising neural network. The human characteristic recognising neural network is adapted to process the sequence of feature vectors and generate output data corresponding to at least one human characteristic derived from the sequence of feature vectors.

traducir

METHOD AND DEVICE FOR EFFICIENTLY ASCERTAINING OUTPUT SIGNALS OF A MACHINE LEARNING SYSTEM

Nº publicación: US2020206939A1 02/07/2020

Solicitante:

BOSCH GMBH ROBERT [DE]

CN_110998609_A

Resumen de: US2020206939A1

A method for efficiently ascertaining output signals of a sequence of output signals with the aid of a sequence of layers of a machine learning system, in particular a neural network, from a sequence of input signals. The neural network is supplied in succession with the input signals of the sequence of input signals in a sequence of discrete time increments. At the discrete time increments, signals present in the network are in each case further propagated through a layer of the sequence of layers.

traducir

Página1 de 11 nextPage por página

punteroimgVolver