BR112017019821A2 - atribuição de pontuação de relevância para redes neurais artificiais - Google Patents

atribuição de pontuação de relevância para redes neurais artificiais

Info

Publication number
BR112017019821A2
BR112017019821A2 BR112017019821A BR112017019821A BR112017019821A2 BR 112017019821 A2 BR112017019821 A2 BR 112017019821A2 BR 112017019821 A BR112017019821 A BR 112017019821A BR 112017019821 A BR112017019821 A BR 112017019821A BR 112017019821 A2 BR112017019821 A2 BR 112017019821A2
Authority
BR
Brazil
Prior art keywords
relevance score
artificial neural
neural networks
score assignment
items
Prior art date
Application number
BR112017019821A
Other languages
English (en)
Other versions
BR112017019821B8 (pt
BR112017019821B1 (pt
Inventor
Sebastian Bach
Alexander Binder
Grégoire Montavon
Klaus-Robert Müller
Wojciech Samek
Original Assignee
Fraunhofer Ges Forschung
Univ Berlin Tech
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Fraunhofer Ges Forschung, Univ Berlin Tech filed Critical Fraunhofer Ges Forschung
Publication of BR112017019821A2 publication Critical patent/BR112017019821A2/pt
Publication of BR112017019821B1 publication Critical patent/BR112017019821B1/pt
Publication of BR112017019821B8 publication Critical patent/BR112017019821B8/pt

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/279—Recognition of textual entities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/048—Activation functions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/082—Learning methods modifying the architecture, e.g. adding, deleting or silencing nodes or connections
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
    • G06V10/449—Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters
    • G06V10/451—Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters with interaction between the filter responses, e.g. cortical complex cells
    • G06V10/454—Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/7715—Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/27—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique
    • G10L25/30—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique using neural networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Biophysics (AREA)
  • Mathematical Physics (AREA)
  • Multimedia (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Human Computer Interaction (AREA)
  • Signal Processing (AREA)
  • Acoustics & Sound (AREA)
  • Medical Informatics (AREA)
  • Databases & Information Systems (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Image Analysis (AREA)
  • Computer And Data Communications (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

a tarefa de atribuição de pontuação de relevância a um conjunto de itens sobre o qual uma rede neural artificial é aplicada é obtida pela redistribuição de uma pontuação de relevância inicial derivada da saída de rede, sobre o conjunto de itens, ao propagar de forma reversa a pontuação de relevância inicial através da rede neural artificial para obter, assim, uma pontuação de relevância para cada item. em particular, esta propagação reversa é aplicável a um conjunto mais amplo de redes neurais artificiais e/ou em esforços computacionais inferiores ao realizá-la em uma forma tal que, para cada neurônio, as pontuações de relevância preliminarmente redistribuídas de um conjunto de neurônios vizinhos a jusante do respectivo neurônio sejam distribuídas em um conjunto de neurônios vizinhos a montante do respectivo neurônio, de acordo com uma função de distribuição.
BR112017019821A 2015-03-20 2015-03-20 Atribuição de pontuação de relevância para redes neurais artificiais BR112017019821B8 (pt)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/EP2015/056008 WO2016150472A1 (en) 2015-03-20 2015-03-20 Relevance score assignment for artificial neural network

Publications (3)

Publication Number Publication Date
BR112017019821A2 true BR112017019821A2 (pt) 2018-05-15
BR112017019821B1 BR112017019821B1 (pt) 2023-09-05
BR112017019821B8 BR112017019821B8 (pt) 2024-02-15

Family

ID=52727129

Family Applications (1)

Application Number Title Priority Date Filing Date
BR112017019821A BR112017019821B8 (pt) 2015-03-20 2015-03-20 Atribuição de pontuação de relevância para redes neurais artificiais

Country Status (9)

Country Link
US (1) US12061966B2 (pt)
EP (1) EP3271863B1 (pt)
JP (1) JP6725547B2 (pt)
KR (1) KR102130162B1 (pt)
CN (1) CN107636693B (pt)
BR (1) BR112017019821B8 (pt)
CA (1) CA2979579C (pt)
RU (1) RU2703343C2 (pt)
WO (1) WO2016150472A1 (pt)

Families Citing this family (139)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114758406B (zh) * 2015-05-11 2024-02-23 奇跃公司 用于使用神经网络的生物特征用户识别的设备、方法和系统
GB201620199D0 (en) 2015-12-18 2017-01-11 British Telecomm Autonomic method for managing a computer system
US20170249547A1 (en) * 2016-02-26 2017-08-31 The Board Of Trustees Of The Leland Stanford Junior University Systems and Methods for Holistic Extraction of Features from Neural Networks
CA3015658A1 (en) 2016-03-11 2017-09-14 Magic Leap, Inc. Structure learning in convolutional neural networks
US11086471B2 (en) * 2016-06-06 2021-08-10 Salesforce.Com, Inc. Visualizing neural networks
US10157332B1 (en) 2016-06-06 2018-12-18 A9.Com, Inc. Neural network-based image manipulation
US11023711B2 (en) * 2016-10-10 2021-06-01 University Of Maryland, College Park All-in-one convolutional neural network for face analysis
US10623775B1 (en) * 2016-11-04 2020-04-14 Twitter, Inc. End-to-end video and image compression
CN106686385B (zh) * 2016-12-30 2018-09-25 平安科技（深圳）有限公司 视频压缩感知重构方法及装置
US11615285B2 (en) 2017-01-06 2023-03-28 Ecole Polytechnique Federale De Lausanne (Epfl) Generating and identifying functional subnetworks within structural networks
CN110574041B (zh) 2017-02-23 2023-06-20 诺基亚技术有限公司 针对深度学习领域的协同激活
US10140709B2 (en) * 2017-02-27 2018-11-27 International Business Machines Corporation Automatic detection and semantic description of lesions using a convolutional neural network
US10540961B2 (en) * 2017-03-13 2020-01-21 Baidu Usa Llc Convolutional recurrent neural networks for small-footprint keyword spotting
JP6915349B2 (ja) * 2017-04-04 2021-08-04 コニカミノルタ株式会社 画像処理装置、画像処理方法、及び画像処理プログラム
EP3399465A1 (en) * 2017-05-05 2018-11-07 Dassault Systèmes Forming a dataset for fully-supervised learning
EP3270308B9 (en) * 2017-06-14 2022-05-18 Siemens Healthcare GmbH Method for providing a secondary parameter, decision support system, computer-readable medium and computer program product
US10728553B2 (en) 2017-07-11 2020-07-28 Sony Corporation Visual quality preserving quantization parameter prediction with deep neural network
KR101880901B1 (ko) * 2017-08-09 2018-07-23 펜타시큐리티시스템 주식회사 기계 학습 방법 및 장치
EP3682271B1 (en) * 2017-09-12 2024-02-14 Services Pétroliers Schlumberger Seismic image data interpretation system
US11194330B1 (en) * 2017-11-03 2021-12-07 Hrl Laboratories, Llc System and method for audio classification based on unsupervised attribute learning
KR101880907B1 (ko) * 2017-09-22 2018-08-16 펜타시큐리티시스템 주식회사 비정상 세션 감지 방법
US11200513B2 (en) * 2017-10-13 2021-12-14 Carrier Corporation Real estate image analysis
US10976429B1 (en) * 2017-10-16 2021-04-13 Hrl Laboratories, Llc System and method for synthetic aperture radar target recognition utilizing spiking neuromorphic networks
WO2019076541A1 (en) 2017-10-19 2019-04-25 British Telecommunications Public Limited Company CONSOLIDATION OF ALGORITHM
CN107783960B (zh) * 2017-10-23 2021-07-23 百度在线网络技术（北京）有限公司 用于抽取信息的方法、装置和设备
US10762390B2 (en) 2017-11-22 2020-09-01 Sas Institute Inc. Computer-based visualization of machine-learning models and behavior
CN110326005A (zh) * 2017-12-25 2019-10-11 索尼公司 信息处理设备、信息处理方法及程序
US12106218B2 (en) * 2018-02-19 2024-10-01 International Business Machines Corporation Deep forecasted human behavior from digital content
US10489511B2 (en) 2018-03-01 2019-11-26 Ink Content, Inc. Content editing using AI-based content modeling
US12118047B2 (en) * 2018-04-17 2024-10-15 Yahoo Assets Llc Systems and methods for multi-dimensional electronic content performance predictor and decision automation
CN108562899B (zh) * 2018-04-20 2021-08-20 西安电子科技大学 高分辨极化sar目标图像快速仿真方法
EP3564862A1 (en) * 2018-05-03 2019-11-06 Siemens Aktiengesellschaft Determining influence of attributes in recurrent neural networks trained on therapy prediction
JP7240657B2 (ja) * 2018-05-15 2023-03-16 Ｔｏｋｙｏ Ａｒｔｉｓａｎ Ｉｎｔｅｌｌｉｇｅｎｃｅ株式会社 ニューラルネットワーク回路装置、ニューラルネットワーク、ニューラルネットワーク処理方法およびニューラルネットワークの実行プログラム
EP3794515A1 (en) * 2018-05-17 2021-03-24 FRAUNHOFER-GESELLSCHAFT zur Förderung der angewandten Forschung e.V. Concepts for distributed learning of neural networks and/or transmission of parameterization updates therefor
CN110147872B (zh) * 2018-05-18 2020-07-17 中科寒武纪科技股份有限公司 编码存储装置及方法、处理器及训练方法
KR102177728B1 (ko) 2018-05-25 2020-11-12 서강대학교 산학협력단 합성곱 신경망을 활용한 데이터 확장방법 및 장치
US11972343B2 (en) 2018-06-11 2024-04-30 Inait Sa Encoding and decoding information
US11663478B2 (en) 2018-06-11 2023-05-30 Inait Sa Characterizing activity in a recurrent artificial neural network
US11893471B2 (en) 2018-06-11 2024-02-06 Inait Sa Encoding and decoding information and artificial neural networks
DE102019205079A1 (de) * 2018-06-19 2019-12-19 Robert Bosch Gmbh Selektive Deaktivierung von Recheneinheiten für künstliche neuronale Netzwerke
US11823038B2 (en) 2018-06-22 2023-11-21 International Business Machines Corporation Managing datasets of a cognitive storage system with a spiking neural network
EP3818478A1 (en) 2018-07-04 2021-05-12 Solmaz Gumruk Musavirligi A.S. A method using artificial neural networks to find a unique harmonized system code from given texts and system for implementing the same
KR102637105B1 (ko) * 2018-07-13 2024-02-15 삼성전자주식회사 영상 데이터를 처리하는 방법 및 장치
IT201800007377A1 (it) * 2018-07-20 2020-01-20 Rete neurale avente un numero ridotto di parametri
DE102018213056A1 (de) * 2018-08-03 2020-02-06 Robert Bosch Gmbh Verfahren und Vorrichtung zum Ermitteln einer Erklärungskarte
DE102018213052A1 (de) * 2018-08-03 2020-02-06 Robert Bosch Gmbh Verfahren und Vorrichtung zum Ermitteln einer Erklärungskarte
KR102547802B1 (ko) * 2018-08-23 2023-06-26 삼성전자주식회사 뉴럴 네트워크를 이용하여 화학 구조를 생성하는 장치 및 방법
US10311337B1 (en) * 2018-09-04 2019-06-04 StradVision, Inc. Method and device for providing integrated feature map using ensemble of multiple outputs from convolutional neural network
EP3620983B1 (en) * 2018-09-05 2023-10-25 Sartorius Stedim Data Analytics AB Computer-implemented method, computer program product and system for data analysis
US10909671B2 (en) * 2018-10-02 2021-02-02 International Business Machines Corporation Region of interest weighted anomaly detection
US11436495B2 (en) * 2018-10-02 2022-09-06 Insitu, Inc. a subsidiary of The Boeing Company Change detection in digital images
KR102248796B1 (ko) * 2018-10-31 2021-05-07 울산과학기술원 사용자의 의사결정 예측 방법 및 장치
US11550970B2 (en) * 2018-11-02 2023-01-10 Wells Fargo Bank, N.A. Resolving opaqueness of complex machine learning applications
EP3881161A1 (en) * 2018-11-14 2021-09-22 Cape Analytics, Inc. Systems, methods, and computer readable media for predictive analytics and change detection from remotely sensed imagery
WO2020110776A1 (ja) * 2018-11-28 2020-06-04 富士フイルム株式会社 分類装置、分類方法及びプログラム、分類結果表示装置
US11087170B2 (en) * 2018-12-03 2021-08-10 Advanced Micro Devices, Inc. Deliberate conditional poison training for generative models
KR102175997B1 (ko) * 2018-12-13 2020-11-06 성균관대학교산학협력단 뇌파 기반의 사용자 의도 인식 방법 및 장치
DE102018221920A1 (de) * 2018-12-17 2020-06-18 Robert Bosch Gmbh Inhaltsadaptive verlustbehaftete Kompression von Messdaten
FI3671536T3 (fi) 2018-12-20 2024-06-18 Optos Plc Patologioiden havaitseminen okulaarikuvissa
US11455538B2 (en) * 2018-12-20 2022-09-27 GM Global Technology Operations LLC Correctness preserving optimization of deep neural networks
LU101088B1 (en) * 2019-01-04 2020-07-07 Iee Sa Method and System for Processing Neural Network Predictions in the Presence of Adverse Perturbations
US20200242771A1 (en) * 2019-01-25 2020-07-30 Nvidia Corporation Semantic image synthesis for generating substantially photorealistic images using neural networks
US11687783B2 (en) * 2019-02-04 2023-06-27 International Business Machines Corporation L2-nonexpansive neural networks
CN113728335A (zh) * 2019-02-08 2021-11-30 新加坡健康服务有限公司 用于3d图像的分类和可视化的方法和系统
US20200278423A1 (en) * 2019-03-01 2020-09-03 GM Global Technology Operations LLC Removing false alarms at the beamforming stage for sensing radars using a deep neural network
CN109977232B (zh) * 2019-03-06 2022-05-10 中南大学 一种基于力导图的图神经网络可视分析方法
US11652603B2 (en) 2019-03-18 2023-05-16 Inait Sa Homomorphic encryption
US11569978B2 (en) 2019-03-18 2023-01-31 Inait Sa Encrypting and decrypting information
WO2020191101A1 (en) 2019-03-18 2020-09-24 Geomagical Labs, Inc. Virtual interaction with three-dimensional indoor room imagery
CA3134440A1 (en) 2019-03-18 2020-09-24 Geomagical Labs, Inc. System and method for virtual modeling of indoor scenes from imagery
JP7205328B2 (ja) * 2019-03-19 2023-01-17 富士通株式会社 推定プログラム、推定装置および推定方法
CN109992642B (zh) * 2019-03-29 2022-11-18 华南理工大学 一种基于科技词条的单任务专家自动遴选方法及系统
US11631266B2 (en) * 2019-04-02 2023-04-18 Wilco Source Inc Automated document intake and processing system
US11645510B2 (en) * 2019-04-08 2023-05-09 Mipsology SAS Accelerating neuron computations in artificial neural networks by selecting input data
EP3726433A1 (en) * 2019-04-17 2020-10-21 Siemens Aktiengesellschaft A method for computer-implemented analysis of a classification model
US11494616B2 (en) * 2019-05-09 2022-11-08 Shenzhen Malong Technologies Co., Ltd. Decoupling category-wise independence and relevance with self-attention for multi-label image classification
CN113874883A (zh) 2019-05-21 2021-12-31 奇跃公司 手部姿势估计
KR102157441B1 (ko) * 2019-05-31 2020-09-17 이화여자대학교 산학협력단 관련성 전사를 이용한 신경망 학습 방법 및 서비스 장치
US11373390B2 (en) * 2019-06-21 2022-06-28 Adobe Inc. Generating scene graphs from digital images using external knowledge and image reconstruction
US11087183B2 (en) * 2019-06-28 2021-08-10 Wipro Limited Method and system of multi-modality classification using augmented data
EP3767543A1 (en) * 2019-07-17 2021-01-20 Robert Bosch GmbH Device and method for operating a neural network
US11355134B2 (en) * 2019-08-02 2022-06-07 Audioshake, Inc. Deep learning segmentation of audio using magnitude spectrogram
US11521630B2 (en) 2020-10-02 2022-12-06 Audioshake, Inc. Deep learning segmentation of audio using magnitude spectrogram
CN110414618B (zh) * 2019-08-05 2023-07-14 上海图趣信息科技有限公司 一种动态平衡分类数据的神经网络训练系统、方法及存储介质
US11568212B2 (en) * 2019-08-06 2023-01-31 Disney Enterprises, Inc. Techniques for understanding how trained neural networks operate
US11829871B2 (en) * 2019-08-20 2023-11-28 Lg Electronics Inc. Validating performance of a neural network trained using labeled training data
US11222242B2 (en) 2019-08-23 2022-01-11 International Business Machines Corporation Contrastive explanations for images with monotonic attribute functions
GB201912145D0 (en) * 2019-08-23 2019-10-09 Five Ai Ltd Performance testing for robotic systems
CN112418388A (zh) * 2019-08-23 2021-02-26 中兴通讯股份有限公司 一种实现深度卷积神经网络处理的方法及装置
US11551054B2 (en) * 2019-08-27 2023-01-10 International Business Machines Corporation System-aware selective quantization for performance optimized distributed deep learning
US11449578B2 (en) * 2019-09-27 2022-09-20 Botty Todorov DIMANOV Method for inspecting a neural network
US11593673B2 (en) 2019-10-07 2023-02-28 Servicenow Canada Inc. Systems and methods for identifying influential training data points
WO2021083573A1 (en) * 2019-10-30 2021-05-06 British Telecommunications Public Limited Company A computer-implemented method of modifying an algorithm operating on a computing system
US11295199B2 (en) * 2019-12-09 2022-04-05 UMNAI Limited XAI and XNN conversion
US11797827B2 (en) 2019-12-11 2023-10-24 Inait Sa Input into a neural network
US11816553B2 (en) 2019-12-11 2023-11-14 Inait Sa Output from a recurrent neural network
US11651210B2 (en) * 2019-12-11 2023-05-16 Inait Sa Interpreting and improving the processing results of recurrent neural networks
US11580401B2 (en) 2019-12-11 2023-02-14 Inait Sa Distance metrics and clustering in recurrent neural networks
CN115136153A (zh) * 2019-12-11 2022-09-30 英艾特股份公司 构造和操作人工循环神经网络
US11256959B2 (en) * 2019-12-31 2022-02-22 Wipro Limited Method and system for training artificial neural network based image classifier using class-specific relevant features
EP4094194A1 (en) 2020-01-23 2022-11-30 Umnai Limited An explainable neural net architecture for multidimensional data
KR20210096342A (ko) * 2020-01-28 2021-08-05 주식회사 딥바이오 뉴런-레벨 가소성 제어를 통해 파국적인 망각을 극복하기 위한 방법 및 이를 수행하는 컴퓨팅 시스템
KR102356438B1 (ko) * 2020-03-10 2022-01-27 연세대학교 산학협력단 요소 간 관계 추출 기반 이종 얼굴 인식 장치 및 방법
US11436830B2 (en) * 2020-03-11 2022-09-06 Bank Of America Corporation Cognitive robotic process automation architecture
US11741340B2 (en) 2020-03-23 2023-08-29 D5Ai Llc Data-dependent node-to-node knowledge sharing by regularization in deep learning
CN111653088B (zh) * 2020-04-21 2022-02-01 长安大学 一种车辆出行量预测模型构建方法及预测方法和系统
CN111291838B (zh) * 2020-05-09 2020-09-01 支付宝(杭州)信息技术有限公司 实体对象分类结果的解释方法和装置
US20210365771A1 (en) * 2020-05-21 2021-11-25 International Business Machines Corporation Out-of-distribution (ood) detection by perturbation
JP7282715B2 (ja) * 2020-06-02 2023-05-29 Kddi株式会社 評価装置、評価方法及び評価プログラム
US20210406661A1 (en) * 2020-06-25 2021-12-30 PolyN Technology Limited Analog Hardware Realization of Neural Networks
US20200327118A1 (en) * 2020-06-27 2020-10-15 Intel Corporation Similarity search using guided reinforcement learning
DE102020208008A1 (de) * 2020-06-29 2021-12-30 Robert Bosch Gesellschaft mit beschränkter Haftung Bildklassifikation und zugehöriges Training für sicherheitsrelevante Klassifikationsaufgaben
CN111754356A (zh) * 2020-06-30 2020-10-09 复旦大学 边符号预测方法、装置及设备
US11250475B2 (en) * 2020-07-01 2022-02-15 Deepmind Technologies Limited Neural network architecture for efficient resource allocation
DE102020210732A1 (de) 2020-08-25 2022-03-03 Robert Bosch Gesellschaft mit beschränkter Haftung Verfahren zur Messung der Relevanz von Bildbereichen für Entscheidungen eines Bildklassifikators
CN112052957B (zh) * 2020-09-02 2023-08-04 平安科技（深圳）有限公司 深度学习模型的可解释性参数获取方法及装置
AU2021346958A1 (en) * 2020-09-24 2023-03-16 Thomson Reuters Enterprise Centre Gmbh Systems and methods for analysis explainability
CN112257863B (zh) * 2020-10-09 2023-04-07 天津大学 网络参数确定方法、装置、区块链的节点及存储介质
KR102344718B1 (ko) * 2020-10-30 2021-12-30 주식회사 아이싸이랩 동물을 식별 및 인증 중 적어도 하나를 수행하기 위해 획득한 동물 이미지를 클러스터링하는 방법
DE102020213830A1 (de) 2020-11-03 2022-05-05 Volkswagen Aktiengesellschaft Verfahren und System zur Bereitstellung einer Diagnoseinformation
CN112270406B (zh) * 2020-11-11 2023-05-23 浙江大学 一种类脑计算机操作系统的神经信息可视化方法
DE102020214944A1 (de) 2020-11-27 2022-06-02 Robert Bosch Gesellschaft mit beschränkter Haftung Bestimmung der für einen Bildklassifikator entscheidungsrelevanten Bildanteile mit vermindertem Rechenzeitbedarf
KR102314713B1 (ko) * 2020-12-24 2021-10-20 한국방송공사 스트리밍을 위한 영상 데이터 패킹 방법 및 이를 이용한 전자 장치
WO2022146031A1 (en) * 2020-12-29 2022-07-07 Samsung Electronics Co., Ltd. Method and device of computing layout selection for efficient dnn inference
KR102446792B1 (ko) * 2021-03-23 2022-09-22 연세대학교 산학협력단 인공 신경망을 설명하기 위한 관련성 가중 클래스 활성화 맵 생성 장치 및 방법
CN115128566A (zh) * 2021-03-24 2022-09-30 索尼集团公司 雷达数据确定电路及雷达数据确定方法
JP7325015B2 (ja) * 2021-03-24 2023-08-14 パナソニックＩｐマネジメント株式会社 量子化方法、量子化装置、及び、プログラム
TWI803852B (zh) * 2021-04-16 2023-06-01 馬爾他商優奈有限公司 可解釋人工智慧及可解釋神經網路轉換
CN115633542B (zh) * 2021-05-04 2024-05-14 谷歌有限责任公司 用于相关和混合的内容项目响应的归因模型
US11475158B1 (en) * 2021-07-26 2022-10-18 Netskope, Inc. Customized deep learning classifier for detecting organization sensitive data in images on premises
KR20230050727A (ko) * 2021-10-08 2023-04-17 삼성전자주식회사 전자 장치 및 전자 장치의 제어 방법
EP4170449B1 (en) * 2021-10-22 2024-01-31 Tata Consultancy Services Limited System and method for ontology guided indoor scene understanding for cognitive robotic tasks
WO2022216521A1 (en) * 2021-11-10 2022-10-13 Innopeak Technology, Inc. Dual-flattening transformer through decomposed row and column queries for semantic segmentation
US11501084B1 (en) 2021-12-08 2022-11-15 Sas Institute Inc. Graphical user interface for visualizing contributing factors to a machine-learning model's output
US20230196062A1 (en) * 2021-12-17 2023-06-22 Sap Se Method and system for global explainability of neural networks
US11861843B2 (en) 2022-01-19 2024-01-02 Cape Analytics, Inc. System and method for object analysis
CN114816963B (zh) * 2022-06-28 2022-09-20 南昌航空大学 嵌入式软件质量评估方法、系统、计算机及可读存储介质
US20240095750A1 (en) * 2022-09-16 2024-03-21 Dell Products L.P. Technical support service location recommendation using machine learning
US20240223780A1 (en) * 2023-01-04 2024-07-04 Meta Platforms Technologies, Llc Generating tile-based region of interest representation of video frames for video encoding

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH08202673A (ja) 1995-01-27 1996-08-09 Matsushita Electric Ind Co Ltd ニューラルネットワークとその学習方法
JPH09330406A (ja) * 1996-06-10 1997-12-22 Fuji Facom Corp 学習支援装置およびパターン認識装置
EP1006458A1 (en) * 1998-12-01 2000-06-07 BRITISH TELECOMMUNICATIONS public limited company Methods and apparatus for information retrieval
US8001121B2 (en) 2006-02-27 2011-08-16 Microsoft Corporation Training a ranking function using propagated document relevance
US7685084B2 (en) * 2007-02-09 2010-03-23 Yahoo! Inc. Term expansion using associative matching of labeled term pairs
EP2260373A4 (en) 2008-02-25 2016-08-03 Atigeo Llc DETERMINING RELEVANT INFORMATION FOR AREAS OF INTEREST
US8812493B2 (en) 2008-04-11 2014-08-19 Microsoft Corporation Search results ranking using editing distance and document information
US8326785B2 (en) * 2008-09-30 2012-12-04 Microsoft Corporation Joint ranking model for multilingual web search
KR101030613B1 (ko) * 2008-10-08 2011-04-20 아이리텍 잉크 아이이미지에서 관심영역정보 및 인식적 정보획득방법
CN102169555B (zh) * 2011-03-30 2013-12-25 华南理工大学 关联性传感信号多传感元件故障定位及传感信号自恢复方法
CN103345656B (zh) 2013-07-17 2016-01-20 中国科学院自动化研究所 一种基于多任务深度神经网络的数据识别方法及装置

Also Published As

Publication number Publication date
US12061966B2 (en) 2024-08-13
BR112017019821B8 (pt) 2024-02-15
RU2017135085A (ru) 2019-04-05
CN107636693B (zh) 2022-01-11
CN107636693A (zh) 2018-01-26
RU2017135085A3 (pt) 2019-04-05
EP3271863A1 (en) 2018-01-24
JP6725547B2 (ja) 2020-07-22
KR102130162B1 (ko) 2020-07-06
BR112017019821B1 (pt) 2023-09-05
KR20170134508A (ko) 2017-12-06
RU2703343C2 (ru) 2019-10-16
CA2979579C (en) 2020-02-18
EP3271863B1 (en) 2021-07-28
US20180018553A1 (en) 2018-01-18
WO2016150472A1 (en) 2016-09-29
JP2018513507A (ja) 2018-05-24
CA2979579A1 (en) 2016-09-29

Similar Documents

Publication Publication Date Title
BR112017019821A2 (pt) atribuição de pontuação de relevância para redes neurais artificiais
CL2020002018A1 (es) Composiciones para modular la expresión de c9orf72. (divisional solicitud 201803582)
BR112018013853A2 (pt) composições e métodos relacionados a sistemas celulares terapêuticos multimodais para indicações de câncer
BR112018004620A2 (pt) moduladores da expressão de kras
GB2550502A (en) Apparatus and methods of data synchronization
BR112016022268A2 (pt) Treinamento, reconhecimento e geração em uma rede de extrema convicção de pico (dbn)
BR112017000229A2 (pt) operação de convolução decomponível em redes neurais
EP4398159A3 (en) Asynchronous deep reinforcement learning
BR112018000241A2 (pt) modelo de recursos de rede para suportar gerenciamento de ciclo de vida de virtualização de função de rede
PH12017000225B1 (en) Social network data processing and profiling
CO2017013065A2 (es) Moduladores de diaciglicerol aciltransferasa 2 (dgat2)
MA53443A (fr) Paquets de messagers végétaux modifiés et utilisations associées
GB2525719A8 (en) Method and system for providing a vulnerability management and verification service
BR112017009795A2 (pt) sistema e método para gerar um perfil de níveis de estresse e de níveis de resiliência de estresse em uma população
BR112017005522A2 (pt) abas de aplicação heterogênea
MX2015008570A (es) Modificacion de consultas de busqueda estructuradas en redes sociales en linea.
BR112016020331A8 (pt) produto compreendendo um item perecível e um revestimento de proteção e método para conservar um produto perecível
BR112017002276A2 (pt) comunicar retorno em redes sem fio
BR112015020394A2 (pt) método para segurança de um primeiro programa, e, produto de software de computador
BR112019002138A2 (pt) método de regulação de característica em plantas
BR112017003163A2 (pt) dispositivo de infraestrutura modular, sistema de infraestrutura e processo para operação de um dispositivo de infraestrutura
BR112018075218A2 (pt) correia transportadora
GB2541616A (en) Data processing system and method for financial or non-financial data
BR112018001970A2 (pt) mecanismo de regras para dispositivos conectados
BR112016015881A2 (pt) Tecnologia inédita de adcc baseada em biologia sintética

Legal Events

Date Code Title Description
B06U Preliminary requirement: requests with searches performed by other patent offices: procedure suspended [chapter 6.21 patent gazette]
B07A Application suspended after technical examination (opinion) [chapter 7.1 patent gazette]
B06A Patent application procedure suspended [chapter 6.1 patent gazette]
B09A Decision: intention to grant [chapter 9.1 patent gazette]
B16A Patent or certificate of addition of invention granted [chapter 16.1 patent gazette]

Free format text: PRAZO DE VALIDADE: 20 (VINTE) ANOS CONTADOS A PARTIR DE 20/03/2015, OBSERVADAS AS CONDICOES LEGAIS

B16C Correction of notification of the grant [chapter 16.3 patent gazette]

Free format text: REF. RPI 2748 DE 05/09/2023 QUANTO AO QUADRO REIVINDICATORIO.