REDES NEURONALES

VolverVolver

Resultados 227 resultados LastUpdate Última actualización 27/05/2020 [03:34:00] pdf PDF xls XLS

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



Página1 de 10 nextPage   por página


IMAGE PROCESSING APPARATUS AND CONTROL METHOD THEREOF

NºPublicación: US2020160096A1 21/05/2020

Solicitante:

SAMSUNG ELECTRONICS CO LTD [KR]

EP_3654240_A1

Resumen de: US2020160096A1

Provided are an image processing apparatus and a control method thereof. The image processing apparatus includes: a communication circuitry configured to communicate with an external device; a storage configured to store data; an image processor configured to perform image processing; and a controller configured to perform an operation, through a neural network, on an image frame contained in an image received by the communication circuitry, to determine a type of the image based on information according to the operation through the neural network, and to control the image processor based on the determined type of the image.

traducir

GENERATING MODIFIED DIGITAL IMAGES UTILIZING A MULTIMODAL SELECTION MODEL BASED ON VERBAL AND GESTURE INPUT

NºPublicación: US2020160042A1 21/05/2020

Solicitante:

ADOBE INC [US]

Resumen de: US2020160042A1

The present disclosure relates to systems, methods, and non-transitory computer readable media for generating modified digital images based on verbal and/or gesture input by utilizing a natural language processing neural network and one or more computer vision neural networks. The disclosed systems can receive verbal input together with gesture input. The disclosed systems can further utilize a natural language processing neural network to generate a verbal command based on verbal input. The disclosed systems can select a particular computer vision neural network based on the verbal input and/or the gesture input. The disclosed systems can apply the selected computer vision neural network to identify pixels within a digital image that correspond to an object indicated by the verbal input and/or gesture input. Utilizing the identified pixels, the disclosed systems can generate a modified digital image by performing one or more editing actions indicated by the verbal input and/or gesture input.

traducir

AUTOMATIC SHIP TRACKING METHOD AND SYSTEM BASED ON DEEP LEARNING NETWORK AND MEAN SHIFT

NºPublicación: US2020160061A1 21/05/2020

Solicitante:

ZHUHAI DA HENGQIN TECH DEVELOPMENT CO LTD [CN]

KR_20200006167_A

Resumen de: US2020160061A1

An automatic ship tracking method and system based on deep learning network and mean shift, wherein the method includes: collecting surveillance video data which includes collecting coastal region surveillance video data under visible light and extracting each frame of image; performing preprocessing to extract a positive sample and a negative sample of a ship target; inputting the samples of the ship target in the video into a neural network to train a model by a region-based convolutional neural network method; extracting initial frame data of the video and performing ship detection and probability density calculation on initial moment data according to the trained model; and determining a ship tracking result at the current moment by a calculation result of a previous moment.

traducir

Road Surface Characterization Using Pose Observations Of Adjacent Vehicles

NºPublicación: US2020160070A1 21/05/2020

Solicitante:

FORD GLOBAL TECH LLC [US]

Resumen de: US2020160070A1

A computing system can crop an image based on a width, height and location of a first vehicle in the image. The computing system can estimate a pose of the first vehicle based on inputting the cropped image and the width, height and location of the first vehicle into a deep neural network. The computing system can then operate a second vehicle based on the estimated pose. The computing system may train a model to identify a type and a location of a hazard according to the estimated pose, the hazard being such things as ice, mud, pothole, or other hazard. The model may be used by an autonomous vehicle to identify and avoid hazards or to provide drive assistance alerts.

traducir

Deep Learning Based Reservoir Modeling

NºPublicación: US2020160173A1 21/05/2020

Solicitante:

LANDMARK GRAPHICS CORP [US]

CA_3067013_A1

Resumen de: US2020160173A1

Embodiments of the subject technology for deep learning based reservoir modelling provides for receiving input data comprising information associated with one or more well logs in a region of interest. The subject technology determines, based at least in part on the input data, an input feature associated with a first deep neural network (DNN) for predicting a value of a property at a location within the region of interest. Further, the subject technology trains, using the input data and based at least in part on the input feature, the first DNN. The subject technology predicts, using the first DNN, the value of the property at the location in the region of interest. The subject technology utilizes a second DNN that classifies facies based on the predicted property in the region of interest.

traducir

SYSTEMS AND METHODS FOR EMPLOYING PREDICATION IN COMPUTATIONAL MODELS

NºPublicación: US2020160848A1 21/05/2020

Solicitante:

FACEBOOK INC [US]

US_2019206390_PA

Resumen de: US2020160848A1

The disclosed method may include (1) determining whether a next operation of a plurality of operations of an artificial neural network (ANN) is dependent upon a Boolean predication value based on a representative value for a weight or an input of a node of the ANN, (2) based on the next operation not being dependent on the Boolean predication value, allowing the next operation to update a state of the ANN, and (3) based on the next operation being dependent on the Boolean predication value, performing at least one of (a) allowing, based on the Boolean predication value being a first value, the next operation to update the state of the ANN, and (b) preventing, based on the Boolean predication value being a second value different from the first value, the next operation from updating the state of the ANN. Various other methods and systems are also disclosed.

traducir

METHOD, SYSTEM AND ARTIFICIAL NEURAL NETWORK

NºPublicación: US2020159490A1 21/05/2020

Solicitante:

SONY CORP [JP]

US_2015278686_PA

Resumen de: US2020159490A1

It is disclosed a method comprising obtaining a target spectrum, obtaining a set of non-target spectra, the set of non-target spectra comprising one or more non-target spectra, summing the target spectrum and the set of non-target spectra to obtain a mixture spectrum, and training an artificial neural network by using the mixture spectrum as input of the neural network and by using a spectrum which is based on the target spectrum as desired output of the artificial neural network.

traducir

DILATED CONVOLUTIONS AND GATING FOR EFFICIENT KEYWORD SPOTTING

NºPublicación: EP3654249A1 20/05/2020

Solicitante:

SNIPS [FR]

Resumen de: EP3654249A1

Method for detection of a keyword in a continuous stream of audio signal, by using a dilated convolutional neural network (DCNN), implemented by one or more computers embedded on a device, the dilated convolutional network (DCNN) comprising a plurality of dilation layers (DL), including an input layer (IL) and an output layer (OL), each layer of the plurality of dilation layers (DL) comprising gated activation units, and skip-connections to the output layer (OL), the dilated convolutional network (DCNN) being configured to generate an output detection signal when a predetermined keyword is present in the continuous stream of audio signal, the generation of the output detection signal being based on a sequence (SSM) of successive measurements (SM) provided to the input layer (IL), each successive measurement (SM) of the sequence (SSM) being measured on a corresponding frame from a sequence of successive frames extracted from the continuous stream of audio signal, at a plurality of successive time steps.

traducir

COMPUTE OPTIMIZATION MECHANISM FOR DEEP NEURAL NETWORKS

NºPublicación: EP3654185A1 20/05/2020

Solicitante:

INTEL CORP [US]

TW_201839607_A

Resumen de: EP3654185A1

An apparatus to facilitate compute optimization is disclosed. The apparatus includes a plurality of processing units each comprising a plurality of execution units (EUs), wherein the plurality of EUs comprise a first EU type and a second EU type

traducir

METHOD AND SYSTEM FOR RECOGNIZING ARRHYTHMIA BY USING ARTIFICIAL NEURAL NETWORKS, AND NON-TRANSITORY COMPUTER-READABLE RECORDING MEDIUM

NºPublicación: KR20200052452A 15/05/2020

Solicitante:

주식회사휴이노

WO_2020091229_A1

Resumen de: WO2020091229A1

According to an embodiment of the present invention, provided is a method for recognizing arrhythmia by using artificial neural networks, the method comprising the steps of: performing a first determination of determining whether at least some of target electrocardiogram signals correspond to an arrhythmic condition by analyzing the target electrocardiogram signals of a subject by using a first artificial neural network trained on the basis of at least one of data about normal electrocardiogram signals and data about arrhythmic electrocardiogram signals; and when the at least some of the target electrocardiogram signals are determined to correspond to an arrhythmic condition, performing a second determination of determining which type of arrhythmic condition the at least some of the target electrocardiogram signals correspond to by analyzing the target electrocardiogram signals by using a second artificial neural network trained on the basis of data about a plurality of types of arrhythmic electrocardiogram signal.

traducir

AN APPARATUS FOR GENERATING TRAINING SET FOR ARTIFICIAL NEURAL NETWORK PERFORMING OBJECT AREA EXTRACTION

NºPublicación: KR20200052416A 15/05/2020

Solicitante:

카페주식회사

Resumen de: KR20200052416A

컴퓨팅 디바이스에 의해 수행되는, 객체 영역 추출을 수행하는 인공 신경망을 위한 학습 데이터를 생성하는 방법이 제공된다. 방법은, 이미지 분류 모델을 이용하여, 적어도 하나의 소스 이미지들에 대해 상기 소스 이미지들 각각에 포함된 객체의 종류를 분류하고, 객체 인식 모델을 이용하여, 상기 적어도 하나의 소스 이미지들에 각각 포함된 객체의 1 차 주석 (Annotation) 데이터를 추출하며, 사용자 단말로 상기 소스 이미지 및 상기 1 차 주석 데이터를 송신하고, 상기 사용자 단말로부터 수신한 정보를 기반으로 상기 소스 이미지에 대한 최종 주석 데이터를 생성하고, 상기 소스 이미지 및 상기 소스 이미지에 대응하는 상기 최종 주석 데이터를 학습 데이터로서 저장한다.

traducir

METHOD OF NEURAL NETWORK CONSTRUCTION FOR THE SIMULATION OF PHYSICAL SYSTEMS

NºPublicación: WO2020094995A1 14/05/2020

Solicitante:

ADAGOS [FR]

Resumen de: WO2020094995A1

The subject of the invention is a method for constructing a forward propagation neural network, a set of nodes and of connection between the nodes forming a topology organized into layers, such that each layer is defined by a set of computable nodes that can be calculated during one and the same step, and the input of a processing node of a layer can be connected to the output of a node of any one of the previous layers, the method comprising a step of initializing a neural network according to an initial topology and at least one topological optimization phase, of which each phase comprises: - at least one additive phase comprising the modification of the topology of the network by the addition of at least one node and/or a connection link between the input of a node of a layer and the output of a node of any one of the previous layers, and/or - at least one subtractive phase comprising the modification of the topology of the network by the deletion of at least one node and/or a connection link between two layers, and in which each topology modification comprises the selecting of a topology modification from among a plurality of candidate modifications, on the basis of an estimation of the variation of the error of the network between each topology modified according to a candidate modification and the previous topology.

traducir

ADAPTIVE BATCH REUSE ON DEEP MEMORIES

NºPublicación: US2020151510A1 14/05/2020

Solicitante:

ADVANCED MICRO DEVICES INC [US]

Resumen de: US2020151510A1

A method of adaptive batch reuse includes prefetching, from a CPU to a GPU, a first plurality of mini-batches comprising a subset of a training dataset. The GPU trains the neural network for the current epoch by reusing, without discard, the first plurality of mini-batches in training the neural network for the current epoch based on a reuse count value. The GPU also runs a validation set to identify a validation error for the current epoch. If the validation error for the current epoch is less than a validation error of a previous epoch, the reuse count value is incremented for a next epoch. However, if the validation error for the current epoch is greater than a validation error of a previous epoch, the reuse count value is decremented for the next epoch.

traducir

SYSTEMS AND METHODS FOR DETERMINING AN ARTIFICIAL INTELLIGENCE MODEL IN A COMMUNICATION SYSTEM

NºPublicación: US2020151551A1 14/05/2020

Solicitante:

GYRFALCON TECH INC [US]

Resumen de: US2020151551A1

A system may include multiple client devices and a processing device communicatively coupled to the client devices. Each client device includes an artificial intelligence (AI) chip and is configured to generate an AI model. The processing device may be configured to (i) receive a respective AI model and an associated performance value of the respective AI model from each of the plurality of client devices; (ii) determine an optimal AI model based on the performance values associated with the respective AI models from the plurality of client devices; and (iii) determine a global AI model based on the optimal AI model. The system may load the global AI model into an AI chip of a client device to cause the client device to perform an AI task based on the global AI model in the AI chip. The AI model may include a convolutional neural network.

traducir

Systems and Methods for Training an Autoencoder Neural Network Using Sparse Data

NºPublicación: WO2020097217A1 14/05/2020

Solicitante:

UNIV EMORY [US]

Resumen de: WO2020097217A1

Methods and systems are provided to prevent pathological overfitting in training autoencoder networks, by forcing the network to only model structure that is shared between different data variables and to enable an automatic search of hyperparameters in training autoencoder networks, resulting in automated discovery of optimally-trained models. The method may include training a neural network. The training may include applying a first binary mask to the set of training data to determine the training input data. The training may include processing the training input data by the neural network to produce network output data. The training may include determining one or more updates of the parameters based on a comparison of at least a portion of the network output data and a corresponding portion of the training data. The portion of the network output data and the corresponding portion of the training input data being inverts.

traducir

DETECTION AND PLANAR REPRESENTATON OF THREE DIMENSIONAL LANES IN A ROAD SCENE

NºPublicación: US2020151465A1 14/05/2020

Solicitante:

GM GLOBAL TECH OPERATIONS LLC [US]

CN_111178122_A

Resumen de: US2020151465A1

A vehicle, system for operating a vehicle and method of navigating a vehicle. The system includes a sensor and a multi-layer convolutional neural network. The sensor generates an image indicative of a road scene of the vehicle. The multi-layer convolutional neural network generates a plurality of feature maps from the image via a first processing pathway, projects at least one of the plurality of feature maps onto a defined plane relative to a defined coordinate system of the road scene to obtain at least one projected feature map, applies a convolution to the at least one projected feature map in a second processing pathway to obtain a final feature map, and determines lane information from the final feature map. A control system adjusts operation of the vehicle using the lane information.

traducir

SYSTEMS, METHODS, AND COMPUTER READABLE MEDIA FOR PREDICTIVE ANALYTICS AND CHANGE DETECTION FROM REMOTELY SENSED IMAGERY

NºPublicación: US2020151500A1 14/05/2020

Solicitante:

CAPE ANALYTICS INC [US]

Resumen de: US2020151500A1

Systems and methods are provided for automatically detecting a change in a feature. For example, a system includes a memory and a processor configured to analyze a change associated with a feature over a period of time using a plurality of remotely sensed time series images. Upon execution, the system would receive a plurality of remotely sensed time series images, extract a feature from the plurality of remotely sensed time series images, generate at least two time series feature vectors based on the feature, where the at least two time series feature vectors correspond to the feature at two different times, create a neural network model configured to predict a change in the feature at a specified time, and determine, using the neural network model, the change in the feature at a specified time based on a change between the at least two time series feature vectors.

traducir

METHODS AND APPARATUS FOR HILN CHARACTERIZATION USING CONVOLUTIONAL NEURAL NETWORK

NºPublicación: US2020151498A1 14/05/2020

Solicitante:

SIEMENS HEALTHCARE DIAGNOSTICS INC [US]

CN_110573859_A

Resumen de: US2020151498A1

A method of characterizing a serum and plasma portion of a specimen in regions occluded by one or more labels. The characterization may be used for determining Hemolysis (H), Icterus (I), and/or Lipemia (L), or Normal (N) of a serum or plasma portion of a specimen. The method includes capturing one or more images of a labeled specimen container including a serum or plasma portion, processing the one or more images with a convolutional neural network to provide a determination of Hemolysis (H), Icterus (I), and/or Lipemia (L), or Normal (N). In further embodiments, the convolutional neural network can provide N-Class segmentation information. Quality check modules and testing apparatus adapted to carry out the method are described, as are other aspects.

traducir

METHOD AND APPARATUS WITH IMAGE RECOGNITION

NºPublicación: US2020151481A1 14/05/2020

Solicitante:

SAMSUNG ELECTRONICS CO LTD [KR]

Resumen de: US2020151481A1

A processor-implemented recognition method includes: receiving query input data; determining a domain to which the query input data belongs using a neural network-based classifier; and in response to the query input data belonging to a first domain, generating second query data of a second domain based on the query input data.

traducir

DARK WEB CONTENT ANALYSIS AND IDENTIFICATION

NºPublicación: US2020151222A1 14/05/2020

Solicitante:

ACCENTURE GLOBAL SOLUTIONS LTD [IE]

Resumen de: US2020151222A1

In some examples, dark web content analysis and identification may include ascertaining data that includes text and images, and analyzing the data by performing deep learning based text and image processing to extract text embedded in the images, and deep embedded clustering to generate clusters. Clusters that are to be monitored may be ascertained from the generated clusters. A determination may be made as to whether the ascertained data is sufficient for classification. If so, a deep convolutional generative adversarial networks (DCGAN) based detector may be utilized to analyze further data with respect to the ascertained clusters, and alternatively, a convolutional neural network (CNN) based detector may be utilized to analyze the further data with respect to the ascertained clusters. Based on the analysis of the further data, an operation associated with a website related to the further data may be controlled.

traducir

IMAGE QUALITY IMPROVEMENT IN CONE BEAM COMPUTED TOMOGRAPHY IMAGES USING DEEP CONVOLUTIONAL NEURAL NETWORKS

NºPublicación: US2020151922A1 14/05/2020

Solicitante:

ELEKTA INC [US]

AU_2017420781_A1

Resumen de: US2020151922A1

Systems and methods include training a deep convolutional neural network (DCNN) to reduce one or more artifacts using a projection space or an image space approach. In a projection space approach, a method can include collecting at least one artifact contaminated cone beam computed tomography (CBCT) projection space image, and at least one corresponding artifact reduced, CBCT projection space image from each patient in a group of patients, and using the artifact contaminated and artifact reduced CBCT projection space images to train a DCNN to reduce artifacts in a projection space image. In an image space approach, a method can include collecting a plurality of CBCT patient anatomical images and corresponding registered computed tomography anatomical images from a group of patients, and using the plurality of CBCT anatomical images and corresponding artifact reduced computed tomography anatomical images to train a DCNN to remove artifacts from a CBCT anatomical image.

traducir

Fully convolutional interest point detection and description via homographic adaptation

NºPublicación: AU2018369757A1 14/05/2020

Solicitante:

MAGIC LEAP INC [US]

WO_2019099515_A1

Resumen de: AU2018369757A1

Systems, devices, and methods for training a neural network and performing image interest point detection and description using the neural network. The neural network may include an interest point detector subnetwork and a descriptor subnetwork. An optical device may include at least one camera for capturing a first image and a second image. A first set of interest points and a first descriptor may be calculated using the neural network based on the first image, and a second set of interest points and a second descriptor may be calculated using the neural network based on the second image. A homography between the first image and the second image may be determined based on the first and second sets of interest points and the first and second descriptors. The optical device may adjust virtual image light being projected onto an eyepiece based on the homography.

traducir

FEATURE DETERMINATION APPARATUS AND METHOD ADAPTED TO MULTIPLE OBJECT SIZES

NºPublicación: US2020151492A1 14/05/2020

Solicitante:

INST INFORMATION IND [TW]

Resumen de: US2020151492A1

A feature determination apparatus and method adapted to multiple object sizes are provided. The apparatus individually supplies each of the object images to a convolution neural network having several convolution layers to generate multiple feature maps corresponding to each object image. The apparatus calculates a feature amount of each feature image of each object image. The apparatus determines an invalid layer start number of each object image according to a preset threshold and the feature amount corresponding to each object image. The apparatus determines a feature map extraction recommendation for each of a plurality of object sizes according to a size of each object image and the invalid layer start number of each object image.

traducir

METHODS AND APPARATUS TO PERFORM IMAGE ANALYSES IN A COMPUTING ENVIRONMENT

NºPublicación: US2020151521A1 14/05/2020

Solicitante:

NIELSEN CO US LLC [US]

Resumen de: US2020151521A1

An apparatus includes a feature extractor to generate image descriptors based on retail product tag images corresponding to a retailer category; a probability density function generator to generate a probability density function of probability values corresponding to visual features represented in the image descriptors; a sample selector to select ones of the probability values based on a sample selection algorithm that identifies positions in the probability density function of the ones of the probability values to be selected; a category signature generator to generate a category signature based on the selected ones of the probability values; and a processor to train a convolutional neural network (CNN) based on a feature descriptor and one of the retail product tag images, the feature descriptor including the category signature concatenated to one of the image descriptors, the training to cause the CNN to classify the one of the retail product tag images as a type of product tag.

traducir

ENVIRONMENT NAVIGATION USING REINFORCEMENT LEARNING

Nº publicación: US2020151515A1 14/05/2020

Solicitante:

DEEPMIND TECH LIMITED [GB]

JP_2019537137_A

Resumen de: US2020151515A1

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a reinforcement learning system. In one aspect, a method of training an action selection policy neural network for use in selecting actions to be performed by an agent navigating through an environment to accomplish one or more goals comprises: receiving an observation image characterizing a current state of the environment; processing, using the action selection policy neural network, an input comprising the observation image to generate an action selection output; processing, using a geometry-prediction neural network, an intermediate output generated by the action selection policy neural network to predict a value of a feature of a geometry of the environment when in the current state; and backpropagating a gradient of a geometry-based auxiliary loss into the action selection policy neural network to determine a geometry-based auxiliary update for current values of the network parameters.

traducir

Página1 de 10 nextPage por página

punteroimgVolver