REDES NEURONALES

VolverVolver

Resultados 197 resultados LastUpdate Última actualización 03/04/2020 [21:47:00] pdf PDF xls XLS

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



Página1 de 8 nextPage   por página


CHARACTER DETECTION DEVICE, METHOD, AND SYSTEM

NºPublicación: WO2020060019A1 26/03/2020

Solicitante:

NAVER CORP [KR]
LINE CORP [JP]

Resumen de: WO2020060019A1

An embodiment provides a character detection method performed by a character detection device, the character detection method comprising the steps of: obtaining an input image; inputting the input image to a character detection model including a neural network and processing the input image; and obtaining at least one output image from the character detection model, wherein the output image includes a probability value image which indicates a probability of existence of a character in the input image and is displayed in an image space at a location corresponding to the input image.

traducir

QUANTIZATION METHOD AND APPARATUS FOR NEURAL NETWORK MODEL IN DEVICE

NºPublicación: WO2020056718A1 26/03/2020

Solicitante:

HUAWEI TECH CO LTD [CN]

Resumen de: WO2020056718A1

A quantization method and apparatus for a neural network model in a device. The method comprises: acquiring user calibration data; inputting the user calibration data into a neural network model, and calculating a quantization parameter of each layer in a plurality of layers of the neural network model; and inputting data to be quantized into the neural network model, and performing quantization on input data of each layer by using the quantization parameter of each layer. The user calibration data is generated according to the data generated by a user using a device, thereby realizing online acquisition of a quantization parameter, and the quantization parameter matches user data of the device, thereby improving quantization accuracy.

traducir

OBJECT TRACKING

NºPublicación: WO2020058560A1 26/03/2020

Solicitante:

NOKIA SOLUTIONS & NETWORKS OY [FI]

Resumen de: WO2020058560A1

An apparatus, method and computer program is described comprising detecting a first object in a first image of a sequence of images using a neural network (22), wherein the means for detecting the first object provides an object area indicative of a first location of the first object; and tracking the first object (24), wherein the means for tracking the first object further comprises generating a predicted future location of the first object and generating an updated location of the first object using the neural network. The means for generating the predicted future location of the first object may, for example, receive said object area indicative of a first location of the first object and may receive said updated location information of the first object.

traducir

PROCESSING OF HISTOLOGY IMAGES WITH A CONVOLUTIONAL NEURAL NETWORK TO IDENTIFY TUMORS

NºPublicación: EP3625765A2 25/03/2020

Solicitante:

LEICA BIOSYSTEMS IMAGING INC [US]

WO_2019133538_A2

Resumen de: US2019206056A1

A convolutional neural network (CNN) is applied to identifying tumors in a histological image. The CNN has one channel assigned to each of a plurality of tissue classes that are to be identified, there being at least one class for each of non-tumorous and tumorous tissue types. Multi-stage convolution is performed on image patches extracted from the histological image followed by multi-stage transpose convolution to recover a layer matched in size to the input image patch. The output image patch thus has a one-to-one pixel-to-pixel correspondence with the input image patch such that each pixel in the output image patch has assigned to it one of the multiple available classes. The output image patches are then assembled into a probability map that can be co-rendered with the histological image either alongside it or over it as an overlay. The probability map can then be stored linked to the histological image.

traducir

TRAINING OF A ONE-SHOT LEARNING CLASSIFIER

NºPublicación: EP3627403A1 25/03/2020

Solicitante:

ELEKTROBIT AUTOMOTIVE GMBH [DE]

Resumen de: EP3627403A1

The present disclosure is related to a method for training a one-shot learning classifier, as well as to a computer program code and a one-shot learning classifier implementing said method. In a first step, an input training sample is received (10) . A set of synthetic training samples is then generated (11) from the input training sample. For this purpose a set of generalization functions is used. Finally, a deep neural network classifier is trained (12) on the set of synthetic training samples.

traducir

CHARACTER IMAGE PROCESSING METHOD AND APPARATUS, DEVICE, AND STORAGE MEDIUM

NºPublicación: US2020089985A1 19/03/2020

Solicitante:

BEIJING SENSETIME TECH DEVELOPMENT CO LTD [CN]

WO_2019119966_PA

Resumen de: US2020089985A1

Provided are character image processing methods and apparatuses, devices, storage medium, and computer programs. The character image processing method mainly comprises: obtaining at least one image block containing a character in a character image to be processed; obtaining image block form transformation information of the image block on the basis of a neural network, the image block form transformation information being used for changing a character orientation in the image block to a predetermined orientation, and the neural network being obtained by means of training using an image block sample having form transformation label information; performing form transformation processing on the character image to be processed according to the image block form transformation information; and performing character recognition on the character image to be processed which is subjected to the form transformation.

traducir

LEARNING UNIFIED EMBEDDING

NºPublicación: US2020090039A1 19/03/2020

Solicitante:

GOOGLE LLC [US]

CN_110506281_A

Resumen de: US2020090039A1

A computer-implemented method for generating a unified machine learning model using a neural network on a data processing apparatus is described. The method includes the data processing apparatus determining respective learning targets for each of a plurality of object verticals. The data processing apparatus determines the respective learning targets based on two or more embedding outputs of the neural network. The method also includes the data processing apparatus training the neural network to identify data associated with each of the plurality of object verticals. The data processing apparatus trains the neural network using the respective learning targets and based on a first loss function. The data processing apparatus uses the neural network trained to generate a unified machine learning model, where the model is configured to identify particular data items associated with each of the plurality of object verticals.

traducir

APPARATUS FOR PROCESSING A SIGNAL

NºPublicación: US2020090040A1 19/03/2020

Solicitante:

NXP BV [NL]
UNIV EINDHOVEN TECH [NL]

EP_3624113_A1

Resumen de: US2020090040A1

An apparatus for processing a signal for input to a neural network, the apparatus configured to: receive a signal comprising a plurality of samples of an analog signal over time; determine at least one frame comprising a group of consecutive samples of the signal, wherein the or each frame includes a first number of samples; for each frame, determine a set of correlation values comprising a second number of correlation values, the second number less than the first number, each correlation value of the set of correlation values based on an autocorrelation of the frame at a plurality of different time lags; provide an output based on the set of correlation values corresponding to the or each of the frames for a neural network for one or more of classification of the analog signal by the neural network and training the neural network based on a predetermined classification.

traducir

END-TO-END TEXT-TO-SPEECH CONVERSION

NºPublicación: AU2020201421A1 19/03/2020

Solicitante:

GOOGLE LLC

KR_20190130634_A

Resumen de: AU2020201421A1

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating speech from text. One of the systems includes one or more computers and one or more storage devices storing instructions that when executed by one or more computers cause the one or more computers to implement: a sequence-to-sequence recurrent neural network configured to: receive a sequence of characters in a particular natural language, and process the sequence of characters to generate a spectrogram of a verbal utterance of the sequence of characters in the particular natural language; and a subsystem configured to: receive the sequence of characters in the particular natural language, and provide the sequence of characters as input to the sequence-to-sequence recurrent neural network to obtain as output the spectrogram of the verbal utterance of the sequence of characters in the particular natural language. WO 2018/183650 PCT/US2018/025101 1/4 0 coo -0 .7- 0 L -0 0 0(1) -(D M zF z u 70 (1 -~ ~ z H) 0* M) U) ) a-U (D~ z (C/) U) (U 0 ~ 0 cE

traducir

NEURAL NETWORK INFERENCING ON PROTECTED DATA

NºPublicación: WO2020055839A1 19/03/2020

Solicitante:

SYNAPTICS INC [US]

US_2020082279_A1

Resumen de: WO2020055839A1

A method and apparatus for inferencing on protected data. A user device retrieves protected data from a secure memory, generates inferences about the protected data using one or more neural network models stored on the user device, and updates a user interface of the user device based at least in part on the inferences. The secure memory is inaccessible to applications executing in a rich environment of the user device. Thus, in some aspects, the inferences may be generated, at least in part, by a neural network application executing in a trusted environment of the user device.

traducir

SCENE CLASSIFICATION PREDICTION

NºPublicación: US2020086879A1 19/03/2020

Solicitante:

HONDA MOTOR CO LTD [JP]

Resumen de: US2020086879A1

Systems and techniques for scene classification and prediction is provided herein. A first series of image frames of an environment from a moving vehicle may be captured. Traffic participants within the environment may be identified and masked based on a first convolutional neural network (CNN). Temporal classification may be performed to generate a series of image frames associated with temporal predictions based on a scene classification model based on CNNs and a long short-term memory (LSTM) network. Additionally, scene classification may occur based on global average pooling. Feature vectors may be generated based on different series of image frames and a fusion feature vector may be obtained by performing data fusion based on a first feature vector, a second feature vector, a third feature vector, etc. In this way, a behavior predictor may generate a predicted driver behavior based on the fusion feature.

traducir

MULTI-TASK MULTI-MODAL MACHINE LEARNING SYSTEM

NºPublicación: US2020089755A1 19/03/2020

Solicitante:

GOOGLE LLC [US]

CN_110574049_A

Resumen de: US2020089755A1

Methods, systems, and apparatus, including computer programs encoded on computer storage media for training a machine learning model to perform multiple machine learning tasks from multiple machine learning domains. One system includes a machine learning model that includes multiple input modality neural networks corresponding to respective different modalities and being configured to map received data inputs of the corresponding modality to mapped data inputs from a unified representation space; an encoder neural network configured to process mapped data inputs from the unified representation space to generate respective encoder data outputs; a decoder neural network configured to process encoder data outputs to generate respective decoder data outputs from the unified representation space; and multiple output modality neural networks corresponding to respective different modalities and being configured to map decoder data outputs to data outputs of the corresponding modality.

traducir

LEARNING METHOD, LEARNING DEVICE WITH MULTI-FEEDING LAYERS AND TESTING METHOD, TESTING DEVICE USING THE SAME

NºPublicación: US2020090047A1 19/03/2020

Solicitante:

STRADVISION INC [KR]

JP_2020047270_A

Resumen de: US2020090047A1

A learning method for a CNN (Convolutional Neural Network) capable of encoding at least one training image with multiple feeding layers, wherein the CNN includes a 1st to an n-th convolutional layers, which respectively generate a 1st to an n-th main feature maps by applying convolution operations to the training image, and a 1st to an h-th feeding layers respectively corresponding to h convolutional layers (1≤h≤(n-1)) is provided. The learning method includes steps of: a learning device instructing the convolutional layers to generate the 1st to the n-th main feature maps, wherein the learning device instructs a k-th convolutional layer to acquire a (k−1)-th main feature map and an m-th sub feature map, and to generate a k-th main feature map by applying the convolution operations to the (k−1)-th integrated feature map generated by integrating the (k−1)-th main feature map and the m-th sub feature map.

traducir

SYSTEMS AND METHODS FOR DETECTION OF STRUCTURES AND/OR PATTERNS IN IMAGES

NºPublicación: US2020090330A1 19/03/2020

Solicitante:

VENTANA MED SYST INC [US]

US_2019012787_A1

Resumen de: US2020090330A1

The subject disclosure presents systems and computer-implemented methods for automatic immune cell detection that is of assistance in clinical immune profile studies. The automatic immune cell detection method involves retrieving a plurality of image channels from a multi-channel image such as an RGB image or biologically meaningful unmixed image. A cell detector is trained to identify the immune cells by a convolutional neural network in one or multiple image channels. Further, the automatic immune cell detection algorithm involves utilizing a non-maximum suppression algorithm to obtain the immune cell coordinates from a probability map of immune cell presence possibility generated from the convolutional neural network classifier.

traducir

VOICE ACTIVITY DETECTION METHOD, METHOD FOR ESTABLISHING VOICE ACTIVITY DETECTION MODEL, COMPUTER DEVICE, AND STORAGE MEDIUM

NºPublicación: US2020090682A1 19/03/2020

Solicitante:

TENCENT TECH SHENZHEN CO LTD [CN]

WO_2019052337_A1

Resumen de: US2020090682A1

A method for establishing a voice activity detection model includes obtaining a training audio file and a target result of the training audio file, framing the training audio file to obtain an audio frame, extracting an audio feature of the audio frame, the audio feature comprising at least two types of features, inputting the extracted audio feature as an input to a deep neural network model, performing information processing on the audio feature through a hidden layer of the deep neural network model, and outputting the processed audio feature through an output layer of the deep neural network model, to obtain a training result; determining a bias between the training result and the target result, and inputting the bias as an input to an error back propagation mechanism, and updating weights of the hidden layer until the deep neural network model reaches a preset condition.

traducir

DEEP NEURAL NETWORK PROCESSING FOR SENSOR BLINDNESS DETECTION IN AUTONOMOUS MACHINE APPLICATIONS

NºPublicación: US2020090322A1 19/03/2020

Solicitante:

NVIDIA CORP [US]

Resumen de: US2020090322A1

In various examples, a deep neural network (DNN) is trained for sensor blindness detection using a region and context-based approach. Using sensor data, the DNN may compute locations of blindness or compromised visibility regions as well as associated blindness classifications and/or blindness attributes associated therewith. In addition, the DNN may predict a usability of each instance of the sensor data for performing one or more operations—such as operations associated with semi-autonomous or autonomous driving. The combination of the outputs of the DNN may be used to filter out instances of the sensor data—or to filter out portions of instances of the sensor data determined to be compromised—that may lead to inaccurate or ineffective results for the one or more operations of the system.

traducir

METHODS, SYSTEMS AND APPARATUS TO IMPROVE CONVOLUTION EFFICIENCY

NºPublicación: US2020089506A1 19/03/2020

Solicitante:

MOVIDIUS LTD [IE]

DE_112018002566_T5

Resumen de: US2020089506A1

Methods, apparatus, systems, and articles of manufacture are disclosed to improve convolution efficiency of a convolution neural network (CNN) accelerator. An example hardware accelerator includes a hardware data path element (DPE) in a DPE array, the hardware DPE including an accumulator, and a multiplier coupled to the accumulator, the multiplier to multiply first inputs including an activation value and a filter coefficient value to generate a first convolution output when the hardware DPE is in a convolution mode, and a controller coupled to the DPE array, the controller to adjust the hardware DPE from the convolution mode to a pooling mode by causing at least one of the multiplier or the accumulator to generate a second convolution output based on second inputs, the second inputs including an output location value of a pool area, at least one of the first inputs different from at least one of the second inputs.

traducir

MULTI-TASK NEURAL NETWORK SYSTEMS WITH TASK-SPECIFIC POLICIES AND A SHARED POLICY

NºPublicación: US2020090048A1 19/03/2020

Solicitante:

DEEPMIND TECH LIMITED [GB]

WO_2018211138_PA

Resumen de: US2020090048A1

A method is proposed for training a multitask computer system, such as a multitask neural network system. The system comprises a set of trainable workers and a shared module. The trainable workers and shared module are trained on a plurality of different tasks, such that each worker learns to perform a corresponding one of the tasks according to a respective task policy, and said shared policy network learns a multitask policy which represents common behavior for the tasks. The coordinated training is performed by optimizing an objective function comprising, for each task: a reward term indicative of an expected reward earned by a worker in performing the corresponding task according to the task policy; and at least one entropy term which regularizes the distribution of the task policy towards the distribution of the multitask policy.

traducir

NEURAL NETWORK-BASED RECOGNITION OF TRADE WORKERS PRESENT ON INDUSTRIAL SITES

NºPublicación: US2020089942A1 19/03/2020

Solicitante:

INDUS AI INC [US]

Resumen de: US2020089942A1

A computer-implemented method and system for neural network-based recognition of trade workers present on industrial sites is presented. In an embodiment, a method comprises: using a computing device, receiving a plurality of digital images depicting a particular worker; using the computing device, based on the plurality of digital images, determining a plurality of key-point sets of the digital images, each of the plurality of key-point sets comprising location information of key points identified within a depiction of the particular worker in a particular digital image; using the computing device, based on the plurality of key-point sets, determining a plurality of trade-specific activities that appear to be performed by the particular worker; using the computing device, based on the plurality of trade-specific activities, determining a plurality of trade probabilities, each trade probability among the trade probabilities indicating a likelihood that the particular worker belongs to a particular trade from among a plurality of different trades.

traducir

Determining Intent from Unstructured Input to Update Heterogeneous Data Stores

NºPublicación: US2020090034A1 19/03/2020

Solicitante:

SALESFORCE COM INC [US]

Resumen de: US2020090034A1

For a database system accessible by one or more users, a neural network model and related method are provided that allow a user of the database system to provide unstructured input in the form of a verbal or textual narrative or utterance that expresses the information in a language and manner that is more comfortable for the user. A portion of the narrative or utterance may relate to one or action items that the user intends to be taken with respect to the database system, such as creating, updating, modifying, or deleting a database item (e.g., contact, calendar item, deal, etc.). The neural model processes the unstructured input (narrative or utterance) and determines or classifies the intent with respect to the action item for the database.

traducir

NEURAL NETWORK-BASED CLASSIFICATION METHOD AND CLASSIFICATION DEVICE THEREOF

NºPublicación: US2020090028A1 19/03/2020

Solicitante:

IND TECH RES INST [TW]

Resumen de: US2020090028A1

A neural network-based classification method, including: obtaining a neural network and a first classifier; inputting input data to the neural network to generate a feature map; cropping the feature map to generate a first cropped part and a second cropped part of the feature map; inputting the first cropped part to the first classifier to generate a first probability vector; inputting the second cropped part to a second classifier to generate a second probability vector, wherein weights of the first classifier are shared with the second classifier; and performing a probability fusion on the first probability vector and the second probability vector to generate an estimated probability vector for determining a class of the input data.

traducir

SYSTEMS AND METHODS FOR PREDICTING VEHICLE TRAJECTORY

NºPublicación: US2020086861A1 19/03/2020

Solicitante:

TOYOTA RES INSTITUTE INC [US]

US_2020089246_A1

Resumen de: US2020086861A1

Systems and methods described herein relate to predicting a trajectory of a vehicle. One embodiment generates first and second predicted vehicle trajectories using respective first and second trajectory predictors based, at least in part, on a plurality of inputs including past trajectory information and vehicle sensor data; generates a confidence score for each of the first and second predicted vehicle trajectories using a confidence estimator that includes a first deep neural network, wherein generating the confidence scores includes computing the confidence scores as a function of time within a predetermined temporal horizon; outputs the first and second predicted vehicle trajectories and their respective confidence scores; and controls operation of the vehicle based, at least in part, on one or more of the first predicted vehicle trajectory, the second predicted vehicle trajectory, the confidence score for the first predicted vehicle trajectory, and the confidence score for the second predicted vehicle trajectory.

traducir

AUTOMATED SIMULATION PIPELINE FOR FAST SIMULATION DRIVEN COMPUTER AIDED DESIGN

NºPublicación: WO2020056107A1 19/03/2020

Solicitante:

SIEMENS AG [DE]
SIEMENS CORP [US]

Resumen de: WO2020056107A1

A computer aided design system for simulation driven design of a three-dimensional (3D) object includes a boundary condition extraction module that extracts a set of boundary conditions for each of a plurality of various known designs of 3D objects related to a new design for a proposed 3D object and generates a set of design independent boundary conditions representative of typical usage of the known designs. Design exploration module generates a plurality of design candidates for the new design. Morphing module transforms design independent boundary conditions into design specific boundary conditions for each of the design candidates. Performance prediction module includes a neural network model trained to predict performance of each design candidate based on learning from prior simulation results of known designs, and generates a set of key performance indicators for each design candidate. A best design choice is selected from the design candidates based on the key performance indicators.

traducir

TRAINING IMAGE-PROCESSING NEURAL NETWORKS BY SYNTHETIC PHOTOREALISTIC INDICIA-BEARING IMAGES

NºPublicación: US2020089998A1 19/03/2020

Solicitante:

ABBYY PRODUCTION LLC [RU]

RU_2709661_C1

Resumen de: US2020089998A1

Systems and methods for training image processing neural networks by synthetic photorealistic indicia-bearing images. An example method comprises: generating an initial set of images, wherein each image of the initial set of images comprises a rendering of a text string; producing an augmented set of images by processing the initial set of images to introduce, into each image of the initial set of image, at least one simulated image defect; generating a training dataset comprising a plurality of pairs of images, wherein each pair of images comprises a first image selected from the initial set of images and a second image selected from the augmented set of images; and training, using the training dataset, a convolutional neural network for image processing.

traducir

VERY DEEP CONVOLUTIONAL NEURAL NETWORKS FOR END-TO-END SPEECH RECOGNITION

Nº publicación: US2020090044A1 19/03/2020

Solicitante:

GOOGLE LLC [US]

JP_2019534472_A

Resumen de: US2020090044A1

A speech recognition neural network system includes an encoder neural network and a decoder neural network. The encoder neural network generates an encoded sequence from an input acoustic sequence that represents an utterance. The input acoustic sequence includes a respective acoustic feature representation at each of a plurality of input time steps, the encoded sequence includes a respective encoded representation at each of a plurality of time reduced time steps, and the number of time reduced time steps is less than the number of input time steps. The encoder neural network includes a time reduction subnetwork, a convolutional LSTM subnetwork, and a network in network subnetwork. The decoder neural network receives the encoded sequence and processes the encoded sequence to generate, for each position in an output sequence order, a set of sub string scores that includes a respective sub string score for each substring in a set of substrings.

traducir

Página1 de 8 nextPage por página

punteroimgVolver