NEURONAL NETWORKS

VolverGo back

Resultados 181 results. LastUpdate Updated on 06/12/2021 [12:50:00] pdf PDF xls XLS

Solicitudes publicadas en los últimos 30 días / Applications published in the last 30 days



Page1/8 nextPage   results/page


DEVICE FOR LOCATING NOISE IN STEERING SYSTEM

Publication No.: US2021370904A1 02/12/2021

Applicant:

HYUNDAI MOBIS CO LTD [KR]

DE_102020134555_PA

Absstract of: US2021370904A1

A device for locating a noise occurring in a steering system includes: a sound receiving unit detecting noise occurring in a steering system; a processing unit inputting data on the noise in the steering system into a neural network model that performs learning in advance and locating a position or a component at which the noise occurs in the steering system, the noise being detected by the sound receiving unit; and a storage unit in which the neural network model that performs the learning in advance is stored.

traducir

ITERATIVE DEEP GRAPH LEARNING FOR GRAPH NEURAL NETWORKS

Publication No.: US2021374499A1 02/12/2021

Applicant:

IBM [US]
RENSSELAER POLYTECH INST [US]

Absstract of: US2021374499A1

An initial noisy graph topology is obtained and an initial adjacency matrix is generated by a similarity learning component using similarity learning and a similarity metric function. An updated adjacency matrix with node embeddings is produced from the initial adjacency matrix using a graph neural network (GNN). The node embeddings are fed back to revise the similarity learning component. The generating, producing, and feeding back operations are repeated for a plurality of iterations.

traducir

SYSTEM, TRAINING DEVICE, TRAINING METHOD, AND PREDICTING DEVICE

Publication No.: US2021374543A1 02/12/2021

Applicant:

PREFERRED NETWORKS INC [JP]

JP_2020135141_A

Absstract of: US2021374543A1

A system includes a first neural network configured to calculate, based on input data, data indicative of a predicted result of a predetermined prediction task for the input data, and a second neural network configured to calculate, based on the input data and labelled data corresponding to the input data, data related to error in the labelled data. At least one of the first neural network or the second neural network is trained by using at least both the data indicative of the predicted result calculated by the first neural network and the data related to the error in the labelled data calculated by the second neural network.

traducir

Systems and Methods for Out-of-Distribution Detection

Publication No.: US2021374524A1 02/12/2021

Applicant:

SALESFORCE COM INC [US]

Absstract of: US2021374524A1

Some embodiments of the current disclosure disclose methods and systems for detecting out-of-distribution (ODD) data. For example, a method for detecting ODD data includes obtaining, at a neural network composed of a plurality of layers, a set of training data generated according to a distribution. Further, the method comprises generating, via a processor, a feature map by combining mapping functions corresponding to the plurality of layers into a vector of mapping function elements and mapping, by the feature map, the set of training data to a set of feature space training data in a feature space. Further, the method comprises identifying, via the processor, a hyper-ellipsoid in the feature space enclosing the feature space training data based on the generated feature map. In addition, the method comprises determining, via the processor, the first test data sample is OOD data when a mapped first test data sample in the feature space is outside the hyper-ellipsoid.

traducir

TECHNIQUES FOR MODIFYING AND TRAINING A NEURAL NETWORK

Publication No.: US2021374518A1 02/12/2021

Applicant:

NVIDIA CORP [US]

DE_102021113105_PA

Absstract of: US2021374518A1

Apparatuses, systems, and techniques are described herein to speed up inferencing in a neural network by copying output from one layer of the neural network to another computing resource based on dependencies among layers in the network. In at least one embodiment, a processor comprising one or more circuits causes two or more subsequent layers of one or more neural networks to be performed on separate computing resources from a previous layer of the one or more neural networks.

traducir

LEARNING METHOD, ASSOCIATED RECOGNITION METHOD, CORRESPONDING DEVICES

Publication No.: WO2021239579A1 02/12/2021

Applicant:

FOND B COM [FR]

FR_3110991_A1

Absstract of: WO2021239579A1

The invention relates to a method for learning a plurality of classes for a neural network from time sequences, called learning sequences, formed by successive representations of a scene, with each learning sequence being associated with one of the classes. The method comprises the following steps, for each learning sequence: - obtaining (E0) at least two descriptors from representations of the considered learning sequence; - preliminary learning (E1) of a time dependence value for at least two neural networks, called preliminary neural networks, each receiving one of the descriptors, each time dependence value characterising a relation between at least two values taken by a descriptor at at least two different instants, in order to obtain the optimal values of preliminary parameters associated with the neurons of the preliminary neural networks; - learning (E2) the plurality of classes for a neural network in order to obtain optimal values of parameters, called main parameters, associated with the neurons of the neural network, said neural network being coupled to at least two other neural networks each receiving one of the descriptors, with the parameters associated with the neurons of the other neural networks being set using the optimal values of the preliminary parameters.

traducir

METHOD, COMPUTER PROGRAM AND DEVICE FOR EVALUATING THE ROBUSTNESS OF A NEURAL NETWORK AGAINST IMAGE DISTURBANCES

Publication No.: US2021374482A1 02/12/2021

Applicant:

BULL SAS [FR]

Absstract of: US2021374482A1

The invention relates to a method (100) for evaluating the robustness of a neural network (102) used for image processing against a group of at least two different disturbances that can be found in images, said method (100) comprising the following steps:determining a robustness score (SRIi), called individual robustness score, of said neural network (102) for each disturbance (Pi) in said group;determining at least one similarity score (SSIi,j), called individual similarity score, for the similarity between two disturbances in said group; andcalculating a robustness score (SRG), called overall robustness score, of said neural network (102) against said group of disturbances as a function of:the individual robustness scores (SRIi) for all the disturbances (P), andat least one individual similarity score (SSIi,j) for the similarity between two disturbances.It also relates to a computer program and a device implementing such a method.

traducir

Methods for Image Segmentation, Computer Devices, and Storage Mediums

Publication No.: US2021374478A1 02/12/2021

Applicant:

UNIV SHENZHEN [CN]

WO_2019218136_PA

Absstract of: US2021374478A1

Methods for image segmentation, computer devices, and storage mediums. The method includes acquiring a to-be-segmented image, inputting the to-be-segmented image into an input variable of a full convolution neural network and outputting a convolution characteristic pattern; inputting the convolution characteristic pattern into an input variable of a context-switchable neural network and outputting context expression information; and generating an intermediate characteristic pattern for image segmentation according to the convolution characteristic pattern and the context expression information.

traducir

SYSTEMS AND METHODS FOR CREATING TRAINING DATA

Publication No.: US2021374472A1 02/12/2021

Applicant:

PLUS ONE ROOTICS INC [US]
PLUS ONE ROBOTICS INC [US]

US_2021201077_A1

Absstract of: US2021374472A1

Training images can be synthesized in order to obtain enough data to train a model (e.g., a neural network) to recognize various classifications of a type of object. Images can be synthesized by blending images of objects labeled using those classifications into selected background images. To improve results, one or more operations are performed to determine whether the synthesized images can still be used as training data, such as by verifying one or more objects of interested represented in those images is not occluded, or at least satisfies a threshold level of acceptance. The training images can be used with real world images to train the model.

traducir

METHOD, APPARATUS, AND ELECTRONIC DEVICE FOR TRAINING NEURAL NETWORK MODEL

Publication No.: US2021374474A1 02/12/2021

Applicant:

TENCENT TECH SHENZHEN CO LTD [CN]

WO_2020259582_A1

Absstract of: US2021374474A1

The present disclosure relates to a method for training a neural network model performed at an electronic device. The method includes: performing initial training by using a first training sample set to obtain an initial neural network model; performing a prediction on a second training sample set by using the initial neural network model to obtain a prediction result of each of training samples in the second training sample set; determining a plurality of preferred samples from the second training sample set based on the prediction results; adding the plurality of preferred samples that are annotated to the first training sample set to obtain an expanded first training sample set; updating training of the initial neural network model by using the expanded first training sample set to obtain an updated neural network model until a training ending condition is satisfied.

traducir

IMAGE ANALYSIS USING DEVIATION FROM NORMAL DATA

Publication No.: US2021374505A1 02/12/2021

Applicant:

GEN ELECTRIC [US]

JP_2021500662_A

Absstract of: US2021374505A1

Systems and techniques for facilitating image analysis using deviation from normal data are presented. In one example, a system generates atlas map data indicative of an atlas map that includes a first portion of patient image data from a plurality of reference patients and a second portion of the patient image data from a plurality of target patients. The first portion of the patient image data is matched to a corresponding age group for a set of patient identities associated with the first portion of the patient image data. The system also generates deviation map data that represents an amount of deviation for the second portion of the patient image data compared to the first portion of the patient image data. Furthermore, the system trains a neural network based on the deviation map data to determine one or more clinical conditions.

traducir

WATERMARK AS HONEYPOT FOR ADVERSARIAL DEFENSE

Publication No.: US2021374501A1 02/12/2021

Applicant:

PAYPAL INC [US]

Absstract of: US2021374501A1

Systems, methods, and computer program products for determining an attack on a neural network. A data sample is received at a first classifier neural network and at a watermark classifier neural network, wherein the first classifier neural network is trained using a first dataset and a watermark dataset. The first classifier neural network determines a classification label for the data sample. A watermark classifier neural network determines a watermark classification label for the data sample. A data sample is determined as an adversarial data sample based on the classification label for the data sample and the watermark classification label for the data sample.

traducir

TECHNIQUE TO PERFORM NEURAL NETWORK ARCHITECTURE SEARCH WITH FEDERATED LEARNING

Publication No.: US2021374502A1 02/12/2021

Applicant:

NVIDIA CORP [US]

Absstract of: US2021374502A1

Apparatuses, systems, and techniques to select a nueral network architecture from a plurality of neural networs in a federated learning (FL) settng. In at least one embodiment, a neural network is trained by combining training resutls from different FL computing systesms, where each of the different FL computing systems, for example, trains different portions of the nerual network.

traducir

METHOD FOR REPRODUCIBILITY OF DEEP LEARNING CLASSIFIERS USING ENSEMBLES

Publication No.: US2021374500A1 02/12/2021

Applicant:

HITACHI LTD [JP]

Absstract of: US2021374500A1

Example implementations described herein involve systems and methods for generating an ensemble of deep learning or neural network models, which can involve, for a training set of data, generating a plurality of model samples for the training set of data, the plurality of model samples generated from deep learning or neural network methods; and aggregating output of the model samples to generate an output of the ensemble models.

traducir

VISUAL SIGN LANGUAGE TRANSLATION TRAINING DEVICE AND METHOD

Publication No.: US2021374393A1 02/12/2021

Applicant:

AVODAH INC [US]

US_2020034609_A1

Absstract of: US2021374393A1

Methods, devices and systems for training a pattern recognition system are described. In one example, a method for training a sign language translation system includes generating a three-dimensional (3D) scene that includes a 3D model simulating a gesture that represents a letter, a word, or a phrase in a sign language. The method includes obtaining a value indicative of a total number of training images to be generated, using the value indicative of the total number of training images to determine a plurality of variations of the 3D scene for generating of the training images, applying each of plurality of variations to the 3D scene to produce a plurality of modified 3D scenes, and capturing an image of each of the plurality of modified 3D scenes to form the training images for a neural network of the sign language translation system.

traducir

Semi-Supervised Action-Actor Detection from Tracking Data in Sport

Publication No.: US2021374419A1 02/12/2021

Applicant:

STATS LLC [US]

Absstract of: US2021374419A1

A method and system of generating agent and actions prediction based on multi-agent tracking data are disclosed herein. A computing system retrieves tracking data from a data store. The computing system generates a trained neural network by generating a plurality of training data sets based on the tracking data by converting each frame of data into a matrix representation of the data contained in the frame and learning, by the neural network, a start frame and end frame of each action contained in the frame and its associated actor. The computing system receives target tracking data associated with an event. The target tracking data includes a plurality of actors and a plurality of actions. The computing system generates, via the trained neural network, a target start frame and a target end frame of each action identified in the tracking data and a corresponding actor.

traducir

TECHNIQUES TO PROCESS LAYERS OF A THREE-DIMENSIONAL IMAGE USING ONE OR MORE NEURAL NETWORKS

Publication No.: US2021374384A1 02/12/2021

Applicant:

NVIDIA CORP [US]

Absstract of: US2021374384A1

Apparatuses, systems, and techniques to identify one or more layers of a three-dimensional graphical image to generate a two-dimensional representation. In at least one embodiment, one or more layers of a three-dimensional graphical image are identified to generate one or more two-dimensional representations.

traducir

OPERATING ON A VIDEO FRAME TO GENERATE A FEATURE MAP OF A NEURAL NETWORK

Publication No.: US2021374422A1 02/12/2021

Applicant:

ADVANCED RISC MACH LTD [GB]

Absstract of: US2021374422A1

A method is described for operating on a frame of a video to generate a feature map of a neural network. The method determines if a block of the frame is an inter block or an intra block, and performs an inter block process in the event that the block is an inter block and/or an intra block process in the event that the block is an intra block. The inter block process determines a measure of differences between the block of the frame and a reference block of a reference frame of the video, and performs either a first process or a second process based on the measure to generate a segment of the feature map. The intra block process determines a measure of flatness of the block of the frame, and performs either a third process or a fourth process based on the measure to generate a segment of the feature map.

traducir

TRAINED MODEL CREATION METHOD FOR PERFORMING SPECIFIC FUNCTION FOR ELECTRONIC DEVICE, LEARNING MODEL FOR PERFORMING SAME FUNCTION, EXCLUSIVE CHIP AND OPERATION METHOD FOR SAME, AND ELECTRONIC DEVICE AND SYSTEM

Publication No.: US2021373646A1 02/12/2021

Applicant:

DEEPX CO LTD [KR]

CN_113366508_A

Absstract of: US2021373646A1

A learning model creation method for performing a specific function for an electronic device, according to an embodiment of the present invention, can include the steps of: preparing big data for training an artificial neural network including, in pairs, sensing data received from a random sensing data generation unit for sensing human behaviors and specific function performance determination data for determining whether to perform a specific function of an electronic device with respect to the sensing data; preparing an artificial neural network model, which includes nodes of an input layer through which the sensing data is inputted, nodes of an output layer through which the specific function performance determination data of the electronic device is outputted, and association parameters between the nodes of the input layer and the nodes of the output layer, and calculates inputs of the sensing data for the nodes of the input layer in order to output the specific function performance determination data from the nodes of the output layer; and repeatedly performing a process of inputting the sensing data included in the prepared big data into the nodes of the input layer and outputting the specific function performance determination data that pairs with the sensing data included in the big data from the nodes of the output layer so as to update the association parameters, thereby mechanically training the artificial neural network model.

traducir

COMPUTE OPTIMIZATIONS FOR NEURAL NETWORKS

Publication No.: US2021373886A1 02/12/2021

Applicant:

INTEL CORP [US]

EP_3671439_A1

Absstract of: US2021373886A1

One embodiment provides for a compute apparatus comprising a decode unit to decode a single instruction into a decoded instruction that specifies multiple operands including a multi-bit input value and a ternary weight associated with a neural network and an arithmetic logic unit including a multiplier, an adder, and an accumulator register. To execute the decoded instruction, the multiplier is to perform a multiplication operation on the multi-bit input based on the ternary weight to generate an intermediate product and the adder is to add the intermediate product to a value stored in the accumulator register and update the value stored in the accumulator register.

traducir

BUILDING SYSTEM WITH STRING MAPPING BASED ON A SEQUENCE TO SEQUENCE NEURAL NETWORK

Publication No.: US2021373510A1 02/12/2021

Applicant:

JOHNSON CONTROLS TECH CO [US]

Absstract of: US2021373510A1

A building system including one or more memory devices configured to store instructions that, when executed by one or more processors, cause the one or more processors to receive training data including acronym strings and tag strings, train a sequence to sequence neural network based on the training data, receive an acronym string for labeling, the acronym string comprising a particular plurality of acronyms, and generate a tag string for the acronym string with the sequence to sequence neural network, wherein the sequence to sequence neural network outputs a tag of the tag string for one acronym of the particular plurality of acronyms based on the one acronym and contextual information of the acronym string, wherein the contextual information includes other acronyms of the particular plurality of acronyms.

traducir

LIDAR LOCALIZATION USING 3D CNN NETWORK FOR SOLUTION INFERENCE IN AUTONOMOUS DRIVING VEHICLES

Publication No.: US2021373161A1 02/12/2021

Applicant:

BAIDU USA LLC [US]
BAIDU COM TIMES TECH BEIJING CO LTD [CN]

JP_2021515724_A

Absstract of: US2021373161A1

In one embodiment, a method for solution inference using neural networks in LiDAR localization includes constructing a cost volume in a solution space for a predicted pose of an autonomous driving vehicle (ADV), the cost volume including a number of sub volumes, each sub volume representing a matching cost between a keypoint from an online point cloud and a corresponding keypoint on a pre-built point cloud map. The method further includes regularizing the cost volume using convention neural networks (CNNs) to refine the matching costs; and inferring, from the regularized cost volume, an optimal offset of the predicted pose. The optimal offset can be used to determining a location of the

traducir

SYSTEMS AND METHODS FOR IDENTIFYING BIOACTIVE AGENTS UTILIZING UNBIASED MACHINE LEARNING

Publication No.: US2021372994A1 02/12/2021

Applicant:

UNIV ROCKEFELLER [US]

AU_2019355222_A1

Absstract of: US2021372994A1

Systems and methods for identifying molecules that are biologically active against a disease, where the method can comprise culturing a first mammalian cell population under organoid formation conditions in the presence of a test molecule to obtain a first organoid, wherein the first mammalian cell population, when cultured under the organoid formation conditions in the absence of the test molecule, results in an organoid with a disease phenotype; imaging the first organoid following exposure to the test molecule; analyzing one or more images of the first organoid using a neural network that has been trained to assign a probability score of disease or non-disease ranging between 0% and 100%; assigning the first organoid a probability score ranging between 0% and 100%; wherein the test molecule is biologically active against the disease if the probability score of the first organoid is greater than a cutoff probability score of non-disease or lower than a cutoff probability score of disease.

traducir

CONTENT ANIMATION USING ONE OR MORE NEURAL NETWORKS

Publication No.: US2021375023A1 02/12/2021

Applicant:

NVIDIA CORP [US]

DE_102021205525_PA

Absstract of: US2021375023A1

Apparatuses, systems, and techniques are presented to generate animation. In at least one embodiment, one or more neural networks are used to generate one or more animation representations of one or more textual characters, wherein the one or more animation representations of the one or more textual characters are to be stored and reused to represent the one or more animation representations of the one or more textual characters.

traducir

UNCERTAINTY-REFINED IMAGE SEGMENTATION UNDER DOMAIN SHIFT

Nº publicación: US2021374968A1 02/12/2021

Applicant:

NAT TECH & ENG SOLUTIONS SANDIA LLC [US]

Absstract of: US2021374968A1

A method for digital image segmentation is provided. The method comprises training a neural network for image segmentation with a labeled training dataset from a first domain, wherein a subset of nodes in the neural net are dropped out during training. The neural network receives image data from a second, different domain. A vector of N values that sum to 1 is calculated for each image element, wherein each value represents an image segmentation class. A label is assigned to each image element according to the class with the highest value in the vector. Multiple inferences are performed with active dropout layers for each image element, and an uncertainty value is generated for each image element. The label of any image element with an uncertainty value above a predefined threshold is replaced with a new label corresponding to the class with the next highest value.

traducir

Page1/8 nextPage results/page

punteroimgGo back