NEURONAL NETWORKS

VolverGo back

Resultados 81 results. LastUpdate Updated on 14/08/2022 [16:05:00] pdf PDF xls XLS

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



Page1/4 nextPage   results/page


DEEP NEURAL NETWORK COMPRESSION BASED ON FILTER IMPORTANCE

Publication No.: US2022253708A1 11/08/2022

Applicant:

GE PREC HEALTHCARE LLC [US]

Absstract of: US2022253708A1

Techniques are provided for compressing deep neural networks using a structured filter pruning method that is extensible and effective. According to an embodiment, a computer-implemented method comprises determining, by a system operatively coupled to a processor, importance scores for filters of layers of a neural network model previously trained until convergence for an inferencing task on a training dataset. The method further comprises removing, by the system, a subset of the filters from one or more layers of the layers based on the importance scores associated with the subset failing to satisfy a threshold importance score value. The method further comprises converting, by the system, the neural network model into a compressed neural network model with the subset of the filters removed.

traducir

Intelligent recognition system and method for rock image under polarizing microscope

Publication No.: AU2020406770A1 11/08/2022

Applicant:

UNIV SHANDONG

WO_2021120372_A1

Absstract of: AU2020406770A1

The present disclosure provides an intelligent recognition system and method for a rock image under a polarizing microscope. The system comprises: a microscopic imaging system configured to implement automatic focusing, single polarization, rotation and orthogonal polarization conversion, and photographing of a rock slice, to obtain an image under a petrographic microscope; an image collection system configured to transmit in real time the obtained image under the petrographic microscope to a learning recognition system and a storage unit for storage so as to serve subsequent learning training; and the learning recognition system configured to use a convolutional neural network model as a feature extraction model, distinguish colors and morphological structures of different rocks and differences thereof under a polarizing microscope by performing feature learning training on different rock images, integrate feature quantities, and establish a rock image recognition model under the polarizing microscope so as to automatically recognize the types of rock particles.

traducir

MEDIA ENHANCEMENT USING DISCRIMINATIVE AND GENERATIVE MODELS WITH FEEDBACK

Publication No.: US2022253990A1 11/08/2022

Applicant:

ADOBE INC [US]

Absstract of: US2022253990A1

The present disclosure describes systems and methods for image enhancement. Embodiments of the present disclosure provide an image enhancement system with a feedback mechanism that provides quantifiable image enhancement information. An image enhancement system may include a discriminator network that determines the quality of the media object. In cases where the discriminator network determines that the media object has a low image quality score (e.g., an image quality score below a quality threshold), the image enhancement system may perform enhancement on the media object using an enhancement network (e.g., using an enhancement network that includes a generative neural network or a generative adversarial network (GAN) model). The discriminator network may then generate an enhancement score for the enhanced media object that may be provided to the user as a feedback mechanism (e.g., where the enhancement score generated by the discriminator network quantifies the enhancement performed by the enhancement network).

traducir

ANALYSIS OF AIRCRAFT TRAJECTORIES

Publication No.: US2022254259A1 11/08/2022

Applicant:

THALES SA [FR]

DE_112020003529_T5

Absstract of: US2022254259A1

Devices and computer-implemented methods for analyzing aircraft trajectories, the method includes the steps of receiving data associated with a plurality of aircraft trajectories; breaking the trajectories down into a plurality of vectors, a vector comprising one or more sequences of enumerators; aligning multiple vectorized trajectories by shifting sequences of enumerators by one or more positions; and detecting one or more anomalies in one or more trajectories by unsupervised classification (e.g. DBSCAN). Developments describe the supervised determination of trajectory anomaly detection models, the use of density-based algorithms, the use of one or more neural networks and/or decision trees, one or more display steps, notably displaying root causes (explainable or understandable artificial intelligence), the processing of avionics data flows, etc. System (e.g. computing) and software aspects are described.

traducir

FEW-SHOT DIGITAL IMAGE GENERATION USING GAN-TO-GAN TRANSLATION

Publication No.: US2022254071A1 11/08/2022

Applicant:

ADOBE INC [US]

Absstract of: US2022254071A1

The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately and efficiently modifying a generative adversarial neural network using few-shot adaptation to generate digital images corresponding to a target domain while maintaining diversity of a source domain and realism of the target domain. In particular, the disclosed systems utilize a generative adversarial neural network with parameters learned from a large source domain. The disclosed systems preserve relative similarities and differences between digital images in the source domain using a cross-domain distance consistency loss. In addition, the disclosed systems utilize an anchor-based strategy to encourage different levels or measures of realism over digital images generated from latent vectors in different regions of a latent space.

traducir

SPARSE AND DIFFERENTIABLE MIXTURE OF EXPERTS NEURAL NETWORKS

Publication No.: US2022253680A1 11/08/2022

Applicant:

GOOGLE LLC [US]

Absstract of: US2022253680A1

A system including a main neural network for performing one or more machine learning tasks on a network input to generate one or more network outputs. The main neural network includes a Mixture of Experts (MoE) subnetwork that includes a plurality of expert neural networks and a gating subsystem. The gating subsystem is configured to: apply a softmax function to a set of gating parameters having learned values to generate a respective softmax score for each of one or more of the plurality of expert neural networks; determine a respective weight for each of the one or more of the plurality of expert neural networks; select a proper subset of the plurality of expert neural networks; and combine the respective expert outputs generated by the one or more expert neural networks in the proper subset to generate one or more MoE outputs.

traducir

Deep Learning Architecture For Analyzing Medical Images For Body Region Recognition And Delineation

Publication No.: US2022254026A1 11/08/2022

Applicant:

UNIV PENNSYLVANIA [US]

Absstract of: US2022254026A1

Provided are systems and methods for analyzing medical images to localize body regions using deep learning techniques. A combination of convolutional neural network (CNN) and a recurrent neural network (RNN) can be applied to medical images, identifying axial slices of a body region. In accordance with embodiments, boundaries, e.g., superior and inferior boundaries of various body regions in computed tomography images can be automatically demarcated.

traducir

Master transform architecture for deep learning

Publication No.: AU2020404935A1 11/08/2022

Applicant:

NVIDIA CORP

CN_114868114_PA

Absstract of: AU2020404935A1

Apparatuses, systems, and techniques to transform input data for training neural networks. In at least one embodiment, one or more data transforms are identified in a sequence of data transforms and combined into one or more master data transforms to be performed by one or more parallel processing units in order to prepare data for training an untrained neural network.

traducir

DETERMINING VISUALLY SIMILAR PRODUCTS

Publication No.: US2022253643A1 11/08/2022

Applicant:

HOME DEPOT PRODUCT AUTHORITY LLC [US]

WO_2021150939_A1

Absstract of: US2022253643A1

A computer-implemented method for determining image similarity includes determining, by a first neural network, a first feature value associated with a first characteristic of a first product based on an image of the first product. The method also includes determining, by a second neural network, a second feature value associated with a second characteristic of the first product based on the image of the first product. The method further involves calculating a first vector space distance between the first feature value and a third feature value associated with the first characteristic of a second product, and calculating a second vector space distance between the second feature value and a fourth feature value associated with the second characteristic of the second product. Additionally, the method includes determining a similarity value based on the first vector space distance and the second vector space distance.

traducir

DISTANCE TO OBSTACLE DETECTION IN AUTONOMOUS MACHINE APPLICATIONS

Publication No.: US2022253706A1 11/08/2022

Applicant:

NVIDIA CORP [US]

US_2022019893_A1

Absstract of: US2022253706A1

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

INTELLIGENT TRANSPORTATION SYSTEMS

Publication No.: US2022252417A1 11/08/2022

Applicant:

STRONG FORCE INTELLECTUAL CAPITAL LLC [US]

CA_3143234_PA

Absstract of: US2022252417A1

Transportation systems have artificial intelligence including neural networks for recognition and classification of objects and behavior including natural language processing and computer vision systems. The transportation systems involve sets of complex chemical processes, mechanical systems, and interactions with behaviors of operators. System-level interactions and behaviors are classified, predicted and optimized using neural networks and other artificial intelligence systems through selective deployment, as well as hybrids and combinations of the artificial intelligence systems, neural networks, expert systems, cognitive systems, genetic algorithms and deep learning.

traducir

ON-DEVICE ACTIVITY RECOGNITION

Publication No.: US2022249906A1 11/08/2022

Applicant:

GOOGLE LLC [US]

CN_113946218_PA

Absstract of: US2022249906A1

A computing device may receive motion data generated by one or more motion sensors that correspond to movement sensed by the one or more motion sensors. The computing device may perform, using one or more neural networks trained with differential privacy, on-device activity recognition to recognize a physical activity that corresponds to the motion data. The computing device may, in response to recognizing the physical activity that corresponds to the motion data, perform an operation associated with the physical activity.

traducir

QUANTIFYING PLANT INFESTATION BY ESTIMATING THE NUMBER OF INSECTS ON LEAVES, BY CONVOLUTIONAL NEURAL NETWORKS THAT PROVIDE DENSITY MAPS

Publication No.: EP4038542A1 10/08/2022

Applicant:

BASF SE [DE]

BR_112022002456_A2

Absstract of: EP3798899A1

Quantifying plant infestation is performed by estimating the number of insects (132) on leaves (122) of a plant (112). A computer (202) receives a plant-image (412) taken from a particular plant (112). The computer (202) uses a first convolutional neural network (262/272) to derive a leaf-image (422) with a main leaf. The computer (202) splits the leaf-image into tiles and uses a second network to process the tiles to density maps. The computer (202) combines the density maps to a combined density map in the dimension of the leaf-image and integrates the pixel values to an estimate number of insects for the main leaf. Insect classes (132(1), 132(2)) can be differentiated to fine-tune the quantification to identify class-specific countermeasures.

traducir

High-Level Syntax for Priority Signaling in Neural Network Compression

Publication No.: EP4038553A1 10/08/2022

Applicant:

NOKIA TECHNOLOGIES OY [FI]

CN_114746870_PA

Absstract of: US2021103813A1

Apparatuses, methods, and computer programs for compressing a neural network are disclosed. An apparatus includes at least one processor; and at least one non-transitory memory including computer program code, the memory and the computer program code configured to, with the at least one processor, cause the apparatus to: receive information from a second device, where the information comprises at least one parameter configured to be used for compression of a neural network, where the at least one parameter is in regard to at least one first aspect or task of the neural network; and compress the neural network, where the neural network is compressed based, at least partially, upon the at least one parameter received from the second device. The apparatus may also receive a compressed neural network from the second device, and further compress the compressed neural network based on the information.

traducir

ON-DEVICE ACTIVITY RECOGNITION

Publication No.: EP4040320A1 10/08/2022

Applicant:

GOOGLE LLC [US]

US_2022249906_A1

Absstract of: EP4040320A1

A computing device may receive motion data generated by one or more motion sensors that correspond to movement sensed by the one or more motion sensors. The computing device may perform, using one or more neural networks trained with differential privacy, on-device activity recognition to recognize a physical activity that corresponds to the motion data. The computing device may, in response to recognizing the physical activity that corresponds to the motion data, perform an operation associated with the physical activity.

traducir

METHOD FOR DETERMINING THE ENCODER ARCHITECTURE OF A NEURAL NETWORK

Publication No.: WO2022161891A1 04/08/2022

Applicant:

CONTINENTAL AUTONOMOUS MOBILITY GERMANY GMBH [DE]

EP_4033402_PA

Absstract of: WO2022161891A1

The invention relates to a method for determining the architecture of an encoder (2) of a convolutional neural network (1), the neural network (1) being configured to process multiple different image processing tasks (t1, t2, t3), the method comprising the steps of: - for each image processing task (t1, t2, t3)), calculating characteristic scale distribution based on training data (S10); - generating multiple encoder architecture candidates, each encoder architecture of said encoder architecture candidates comprising at least one shared encoder layer (SL) which provides computational operations for multiple image processing tasks and multiple branches (b1, b2, b3) which span over one or more encoder layers which provide at least partly different computational operations for said image processing tasks, wherein each branch (b1, b2, b3) is associated with a certain image processing task (t1, t2, t3) (S11); - calculating receptive field sizes of the encoder layers of said multiple encoder architectures (S12); - calculating multiple assessment measures, each assessment measure referring to a combination of a certain encoder architecture of said multiple encoder architectures and a certain image processing task (t1, t2, t3), each assessment measure including information regarding the quality of matching of characteristic scale distribution of the image processing task (t1, t2, t3) associated with the assessment measure to the receptive field sizes of the encoder layers of the enco

traducir

TRAINING AND USING A NEURAL NETWORK FOR MANAGING AN ENVIRONMENT IN A COMMUNICATION NETWORK

Publication No.: WO2022161599A1 04/08/2022

Applicant:

ERICSSON TELEFON AB L M [SE]

Absstract of: WO2022161599A1

Computer implemented methods for training a Student Neural Network, SNN, (600, 700, 800), and for managing an environment of a communication network using a trained SNN (900, 1000), are disclosed. The SNN is for generating an action prediction matrix for an environment in a communication network, the action prediction matrix comprising action predictions for a plurality of nodes or resources in the environment. The training method (600, 700, 800) comprises using a Reinforcement Learning process to train a Teacher Neural Network, TNN, to generate an action prediction for a resource or node in the environment (610), and using the trained TNN to generate a first training data set including action predictions for individual nodes or resources (620). The training method further comprises generating a second training data set from the first training data set (630) such that the second training data set includes action prediction matrices, and using the second training data set to update values of the parameters of the SNN (640).

traducir

Method for identifying travel classification based on smartphone travel surveys

Publication No.: US2022248179A1 04/08/2022

Applicant:

UNIV SHANGHAI MARITIME [CN]

CN_113282842_A

Absstract of: US2022248179A1

The present invention discloses a method for identifying travel classification based on smartphone travel surveys. The method takes individual volunteers as the object, GPS information collected by smartphones and instant recall verification features of respondents as the data source. First, travel features, individual features, and family features are determined by GPS data and questionnaire information of volunteers. Then, a training data set is determined by the equal proportion method. Finally, an artificial neural network combined with a particle swarm optimization algorithm is used to detect travel classification from the survey data. The method described in the invention can realize automatic identification of six travel classifications. It is conducive to replace the traditional resident travel survey with the advanced survey method under the environment of big data. At the same time, it provides data foundation for urban management and planning.

traducir

SELECTIVE CONTENT SHARING

Publication No.: US2022247800A1 04/08/2022

Applicant:

AVAYA MAN L P [US]

Absstract of: US2022247800A1

Co-browsing allows a providing party to access visual content on a computing device for sharing with one or more other parties. The parties receiving the shared image may have dissimilar security authorizations. Accordingly, systems and methods are provided that enable shared content, such as a document, web page viewed in a browser, etc., to automatically be redacted to block those parties who are not authorized to view the content. For example, a neural network may be utilized to scan the document and provide specific redacted copies to the parties so each can view the image of the content with unauthorized content redacted.

traducir

COMPUTER AIDED DIAGNOSIS SYSTEM FOR DETECTING TISSUE LESION ON MICROSCOPY IMAGES BASED ON MULTI-RESOLUTION FEATURE FUSION

Publication No.: US2022245809A1 04/08/2022

Applicant:

TENCENT AMERICA LLC [US]

JP_2022530249_A

Absstract of: US2022245809A1

Embodiments of the present disclosure include a method, device and computer readable medium involving receiving image data to detect tissue lesions, passing the image data through at least one first convoluted neural network, segmenting the image data, fusing the segmented image data, and detecting tissue lesions.

traducir

DEEP LEARNING-BASED ROOT CAUSE ANALYSIS OF PROCESS CYCLE IMAGES

Publication No.: US2022245801A1 04/08/2022

Applicant:

ILLUMINA INC [US]

WO_2022165278_A1

Absstract of: US2022245801A1

The technology disclosed relates to training a convolutional neural network (CNN) to identify and classify images of sections of an image generating chip resulting in process cycle failures. The technology disclosed includes creating a training data set of images of dimensions M×N using labeled images of sections of image generating chip of dimensions J×K. The technology disclosed can fill the M×N frames using horizontal and vertical reflections along edges of J×K labeled images positioned in M×N frames. A pretrained CNN is further trained using the training data set. Trained CNN can classify a section image as normal or depicting failure. The technology disclosed can train a root cause CNN to classify process cycle images of sections causing process cycle failure. The trained CNN can classify a section image by root cause of process failure among a plurality of failure categories.

traducir

COMPUTER-IMPLEMENTED METHOD OF HANDLING AN EMERGENCY INCIDENT, COMMUNICATION NETWORK, AND EMERGENCY PROCESSING UNIT

Publication No.: US2022245768A1 04/08/2022

Applicant:

UNIFY PATENTE GMBH & CO KG [DE]

EP_4036791_PA

Absstract of: US2022245768A1

A computer-implemented method of handling an emergency incident rcan include receiving information on an emergency incident that includes at least one image of the emergency incident, applying a Convolutional Neural Network (CNN) object recognition and classification process for identifying and marking objects on the at least one image that are related to the emergency incident and that may cause at least one secondary hazardous situation, processing the data relating to the identified and marked objects by applying a deep learning algorithm to the data in a Relational Network (RN) architecture, wherein the image on the basis of the identified and marked objects is correlated to a set of recognized objects in a database for classifying the emergency. A communication network, communication apparatus, and an emergency processing unit are also provided. Embodiments of such machines and systems can be configured to implement embodiments of the method.

traducir

TRAINING A NEURAL NETWORK WITH REPRESENTATIONS OF USER INTERFACE DEVICES

Publication No.: US2022245404A1 04/08/2022

Applicant:

MAGIC LEAP INC [US]

KR_20220030315_PA

Absstract of: US2022245404A1

Disclosed herein are examples of a wearable display system capable of determining a user interface (UI) event with respect to a virtual UI device (e.g., a button) and a pointer (e.g., a finger or a stylus) using a neural network. The wearable display system can render a representation of the UI device onto an image of the pointer captured when the virtual UI device is shown to the user and the user uses the pointer to interact with the virtual UI device. The representation of the UI device can include concentric shapes (or shapes with similar or the same centers of gravity) of high contrast. The neural network can be trained using training images with representations of virtual UI devices and pointers.

traducir

NEUROMORPHIC COMPUTING USING ELECTROSTATIC MEMS DEVICES

Publication No.: US2022244684A1 04/08/2022

Applicant:

NUTECH VENTURES [US]

US_2020041964_PA

Absstract of: US2022244684A1

A continuous-time recurrent neural network (CTRNN) is described that exploits the nonlinear dynamics of micro-electro-mechanical system (MEMS) devices to model a neuron in accordance with a neuron rate model that is the basis for dynamic field theory. Each MEMS device in the CTRNN is configured to simulate a neuron population by exploiting the characteristics of bi-stability and hysteresis inherent in certain MEMS device structures. In an embodiment, the MEMS device is a microbeam or cantilevered microbeam device that is excited with an alternating current (AC) voltage at or near an electrical resonance frequency associated with the MEMS device. In another embodiment, the MEMS device is an arched microbeam device that is excited with a direct current voltage and exhibits snap-through behavior due to the physical design of the structure. A CTRNN can be implemented using a number of MEMS devices that are interconnected, the connections associated with varying connection coefficients.

traducir

SYSTEMS AND METHODS FOR QUANTIFYING PATIENT IMPROVEMENT THROUGH ARTIFICIAL INTELLIGENCE

Nº publicación: WO2022165366A1 04/08/2022

Applicant:

UNIV NORTHWESTERN [US]
REHABILITATION INST OF CHICAGO DBA SHIRLEY RYAN ABILITYLAB [US]

Absstract of: WO2022165366A1

Examples of a system and methods for quantifying patient improvement via artificial intelligence are disclosed. In general, via at least one processing element, a machine learning model such as a Siamese neural network is trained in view of a cost function to learn on average a maximum difference in outcomes between a patient at different points in time. Given the architecture of the neural network, a plurality of outcome measures generated for a given point in time can be condensed into a single score.

traducir

Page1/4 nextPage results/page

punteroimgGo back