BR112015015230A8 - Sistema e processo para abordar generalização em uma rede neural - Google Patents

Sistema e processo para abordar generalização em uma rede neural

Info

Publication number
BR112015015230A8
BR112015015230A8 BR112015015230A BR112015015230A BR112015015230A8 BR 112015015230 A8 BR112015015230 A8 BR 112015015230A8 BR 112015015230 A BR112015015230 A BR 112015015230A BR 112015015230 A BR112015015230 A BR 112015015230A BR 112015015230 A8 BR112015015230 A8 BR 112015015230A8
Authority
BR
Brazil
Prior art keywords
neural network
generalization
approach
training
feature detectors
Prior art date
Application number
BR112015015230A
Other languages
English (en)
Other versions
BR112015015230A2 (pt
Inventor
E Hinton Geoffrey
Krizhevsky Alexander
Sutskever Ilya
Original Assignee
Google Inc
Google Llc
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 Google Inc, Google Llc filed Critical Google Inc
Publication of BR112015015230A2 publication Critical patent/BR112015015230A2/pt
Publication of BR112015015230A8 publication Critical patent/BR112015015230A8/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
    • G06N3/08—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
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
    • G06F18/24133—Distances to prototypes
    • 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
    • G06N3/045—Combinations of 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
    • G06N3/047—Probabilistic or stochastic 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
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Molecular Biology (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Mathematical Physics (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Probability & Statistics with Applications (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Image Analysis (AREA)
  • Feedback Control In General (AREA)

Abstract

SISTEMA E PROCESSO PARA ABORDAR GENERALIZAÇÃO EM UMA REDE NEURAL. A presente invenção refere-se a um sistema para treinamento de uma rede neural. Uma chave é ligada aos detectores de recursos em pelo menos algumas das camadas da rede neural. Para cada caso de treinamento, a chave seletivamente desabilita aleatoriamente cada um dos detectores de recursos, de acordo com a probabilidade pré-configurada. Os pesos de cada caso de treinamento são depois normalizados para aplicar a rede neural aos dados de teste.
BR112015015230A 2012-12-24 2013-12-23 Sistema e processo para abordar generalização em uma rede neural BR112015015230A8 (pt)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US201261745711P 2012-12-24 2012-12-24
US14/015,768 US9406017B2 (en) 2012-12-24 2013-08-30 System and method for addressing overfitting in a neural network
PCT/US2013/077608 WO2014105866A1 (en) 2012-12-24 2013-12-23 System and method for addressing overfitting in a neural network

Publications (2)

Publication Number Publication Date
BR112015015230A2 BR112015015230A2 (pt) 2017-07-11
BR112015015230A8 true BR112015015230A8 (pt) 2018-01-02

Family

ID=50975834

Family Applications (1)

Application Number Title Priority Date Filing Date
BR112015015230A BR112015015230A8 (pt) 2012-12-24 2013-12-23 Sistema e processo para abordar generalização em uma rede neural

Country Status (4)

Country Link
US (4) US9406017B2 (pt)
AU (1) AU2013370515A1 (pt)
BR (1) BR112015015230A8 (pt)
WO (1) WO2014105866A1 (pt)

Families Citing this family (49)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102239714B1 (ko) * 2014-07-24 2021-04-13 삼성전자주식회사 신경망 학습 방법 및 장치, 데이터 처리 장치
EP3259688A4 (en) 2015-02-19 2018-12-12 Digital Reasoning Systems, Inc. Systems and methods for neural language modeling
US10410118B2 (en) 2015-03-13 2019-09-10 Deep Genomics Incorporated System and method for training neural networks
US10438112B2 (en) 2015-05-26 2019-10-08 Samsung Electronics Co., Ltd. Method and apparatus of learning neural network via hierarchical ensemble learning
US10769531B2 (en) 2015-06-05 2020-09-08 Cisco Technology, Inc. Methods and systems for counting people
US10185803B2 (en) 2015-06-15 2019-01-22 Deep Genomics Incorporated Systems and methods for classifying, prioritizing and interpreting genetic variants and therapies using a deep neural network
US10586151B1 (en) 2015-07-31 2020-03-10 Perceive Corporation Mitigating overfitting in training machine trained networks
US9569696B1 (en) * 2015-08-12 2017-02-14 Yahoo! Inc. Media content analysis system and method
KR102492318B1 (ko) 2015-09-18 2023-01-26 삼성전자주식회사 모델 학습 방법 및 장치, 및 데이터 인식 방법
US9965719B2 (en) * 2015-11-04 2018-05-08 Nec Corporation Subcategory-aware convolutional neural networks for object detection
US10515312B1 (en) * 2015-12-30 2019-12-24 Amazon Technologies, Inc. Neural network model compaction using selective unit removal
JP6610278B2 (ja) 2016-01-18 2019-11-27 富士通株式会社 機械学習装置、機械学習方法及び機械学習プログラム
US10366451B2 (en) 2016-01-27 2019-07-30 Huawei Technologies Co., Ltd. System and method for prediction using synthetic features and gradient boosted decision tree
WO2017152990A1 (en) * 2016-03-11 2017-09-14 Telecom Italia S.P.A. Convolutional neural networks, particularly for image analysis
US9858340B1 (en) 2016-04-11 2018-01-02 Digital Reasoning Systems, Inc. Systems and methods for queryable graph representations of videos
CN109564636B (zh) * 2016-05-31 2023-05-02 微软技术许可有限责任公司 使用一个神经网络来训练另一个神经网络
CN107480686B (zh) * 2016-06-08 2021-03-30 阿里巴巴集团控股有限公司 一种筛选机器学习特征的方法和装置
US10706327B2 (en) 2016-08-03 2020-07-07 Canon Kabushiki Kaisha Information processing apparatus, information processing method, and storage medium
US10909451B2 (en) 2016-09-01 2021-02-02 International Business Machines Corporation Apparatus and method for learning a model corresponding to time-series input data
JP6847386B2 (ja) 2016-09-09 2021-03-24 インターナショナル・ビジネス・マシーンズ・コーポレーションＩｎｔｅｒｎａｔｉｏｎａｌ Ｂｕｓｉｎｅｓｓ Ｍａｃｈｉｎｅｓ Ｃｏｒｐｏｒａｔｉｏｎ ニューラルネットワークの正則化
US10477271B1 (en) 2016-10-12 2019-11-12 Opine Inc. System and method for generating real-time, event and user-based responses and analytics
KR20180069452A (ko) 2016-12-15 2018-06-25 삼성전자주식회사 뉴럴 네트워크의 학습 방법 및 뉴럴 네트워크를 이용한 인식 방법, 및 그 장치
EP3340129B1 (en) * 2016-12-21 2019-01-30 Axis AB Artificial neural network class-based pruning
JP6704341B2 (ja) 2016-12-27 2020-06-03 株式会社デンソーアイティーラボラトリ 情報推定装置及び情報推定方法
JP6729455B2 (ja) 2017-03-15 2020-07-22 株式会社島津製作所 分析データ解析装置及び分析データ解析方法
WO2018199721A1 (ko) * 2017-04-28 2018-11-01 서울대학교 산학협력단 뉴럴네트워크에서 데이터 처리를 가속화하는 방법 및 장치
KR102410820B1 (ko) 2017-08-14 2022-06-20 삼성전자주식회사 뉴럴 네트워크를 이용한 인식 방법 및 장치 및 상기 뉴럴 네트워크를 트레이닝하는 방법 및 장치
US10726335B2 (en) 2017-10-26 2020-07-28 Uber Technologies, Inc. Generating compressed representation neural networks having high degree of accuracy
US11138505B2 (en) * 2017-12-21 2021-10-05 Fujitsu Limited Quantization of neural network parameters
CN108256629B (zh) * 2018-01-17 2020-10-23 厦门大学 基于卷积网络和自编码的eeg信号无监督特征学习方法
US11119915B2 (en) 2018-02-08 2021-09-14 Samsung Electronics Co., Ltd. Dynamic memory mapping for neural networks
US10652617B2 (en) 2018-04-04 2020-05-12 Hulu, LLC Dimensional isolation prediction in video delivery systems
CN108985217A (zh) * 2018-07-10 2018-12-11 常州大学 一种基于深度空间网络的交通标志识别方法及系统
IL296738A (en) * 2018-07-11 2022-11-01 Illumina Inc A framework based on deep learning for the purpose of identifying patterns of sequences that cause
US11313950B2 (en) 2019-01-15 2022-04-26 Image Sensing Systems, Inc. Machine learning based highway radar vehicle classification across multiple lanes and speeds
US10642723B1 (en) 2019-02-05 2020-05-05 Bank Of America Corporation System for metamorphic relationship based code testing using mutant generators
TWI696129B (zh) 2019-03-15 2020-06-11 華邦電子股份有限公司 可執行人工智慧運算的記憶體晶片及其運算方法
JP7106486B2 (ja) 2019-04-22 2022-07-26 株式会社東芝 学習装置、学習方法、プログラムおよび情報処理システム
CN110545426B (zh) * 2019-08-29 2021-04-20 西安电子科技大学 基于编码损伤修复cnn的空域可分级视频编码方法
CN111080976B (zh) * 2019-12-24 2021-09-10 北京优航机电技术有限公司 一种温度变化场景下实时监测天然气泄漏的方法及装置
US11537885B2 (en) 2020-01-27 2022-12-27 GE Precision Healthcare LLC Freeze-out as a regularizer in training neural networks
FI20205426A1 (en) 2020-04-28 2021-10-29 Elisa Oyj Obtaining an autoencoder model for processing target system metrics
US11531734B2 (en) 2020-06-30 2022-12-20 Bank Of America Corporation Determining optimal machine learning models
US11891195B2 (en) * 2020-07-29 2024-02-06 The Boeing Company Mitigating damage to multi-layer networks
CN112183946A (zh) * 2020-09-07 2021-01-05 腾讯音乐娱乐科技（深圳）有限公司 多媒体内容评估方法、装置及其训练方法
KR102390326B1 (ko) * 2020-09-15 2022-04-26 주식회사 뷰노 심전도 데이터 분류를 위한 심층 신경망 사전 학습 방법
CN113256000B (zh) * 2021-05-26 2022-05-20 四川大学 一种带注意力机制序列到序列的景区短期客流量预测方法
DE102022201702A1 (de) 2022-02-18 2023-08-24 Zf Friedrichshafen Ag Computerimplementiertes Verfahren zum Absichern eines Maschinenlernmodells gegen eine Einsatzverlagerung, Computerprogramm, Datenträgersignal und automatisiertes Transportsystem zum Transportieren von Personen und/oder Gegenständen
DE102022207416B3 (de) 2022-07-20 2023-10-05 Zf Friedrichshafen Ag Computerimplementiertes Verfahren zum Erkennen von Verdeckungen eines Bildgebungssensors

Also Published As

Publication number Publication date
US20210224659A1 (en) 2021-07-22
BR112015015230A2 (pt) 2017-07-11
AU2013370515A1 (en) 2015-07-16
US10366329B2 (en) 2019-07-30
US10977557B2 (en) 2021-04-13
US11829882B2 (en) 2023-11-28
WO2014105866A1 (en) 2014-07-03
US20140180986A1 (en) 2014-06-26
US9406017B2 (en) 2016-08-02
US20190347558A1 (en) 2019-11-14
US20160335540A1 (en) 2016-11-17

Similar Documents

Publication Publication Date Title
BR112015015230A8 (pt) Sistema e processo para abordar generalização em uma rede neural
BR112017009869A2 (pt) sistema para gerenciamento de inventário
BR102014017270A8 (pt) aparelho, sistema de sensor de combustível sem fio e método para geração de dados de sensor
BR112015011081A2 (pt) fábrica de análise preditiva
KR20180084799A (ko) 테이블 게임의 관리 시스템, 유기용 대용 화폐, 및 검사 장치
BR112013019922A2 (pt) método e aparelho para um plano de controle para gerenciar segurança baseada em domínio e mobilidade em uma rede central de informação
BR112015005588A2 (pt) sistema e método implementado por computador para perfilamento de utilização de recursos de computação.
BR112016002637A2 (pt) sincronização de barreira com cálculo dinâmico de largura
BR112015024773A8 (pt) Método, sistema e aparelho para comparação de imagens
BR112015013917A2 (pt) método, unidade de computação, e sistema
BR112013017759A2 (pt) sistema, método, e artigo para avisar mudança de comportamento
BR112018003599A2 (pt) método de coleta de dados de sonda e dispositivo para coleta de dados de sonda
BR112016013158A2 (pt) Identificação de candidatos para testes clínicos
BR112016026264A2 (pt) sistema e método dos mesmos para otimizar o tempo de inicialização de computadores com múltiplas cpus.
BR112018017168A2 (pt) emplastro de coloração do sangue, método e dispositivo para teste sanguíneo usando o mesmo
BR112014018729A8 (pt) Método e aparelho para testar materiais de circulação perdidos para formações subterrâneas
BR112015007522A2 (pt) dispositivo de computação , método de análise , produto de programa de computador e sistema de computador
BR112017010363A2 (pt) métodos de mudar taxa de produção de poliolefina com a composição dos agentes de condensação induzidos
BR112017000875A2 (pt) sistemas e métodos para classificação de padrões de dados de resposta locais do sensor, representativos da gravidade da patologia da rede de distribuição
BR112014027086A2 (pt) método implementado por computador, mídia não transitória lida por computador e sistema para definir ponto de checagem
BR112016006482A2 (pt) métodos e aparelho para implementação de indicadores de grupo para modelos neurais
BR112017011910A2 (pt) método para acessar dados em uma memória em um endereço não alinhado
BR112016007137A8 (pt) sistema, meio de armazenamento e método para otimizar transferência de dados em plataformas de computação em nuvem
BR112016016288A8 (pt) método implementado por computador, meio legível por computador não transitório, e dispositivo de computação relativos a metadados de definição de privacidade para desenvolvedores de aplicativo
BR112015028454A2 (pt) dispositivo de computação óptico para a determinação de uma característica de uma amostra, método para a utilização de um dispositivo de computação óptico e método de computação óptico

Legal Events

Date Code Title Description
B25D Requested change of name of applicant approved

Owner name: GOOGLE LLC (US)

B06F Objections, documents and/or translations needed after an examination request according [chapter 6.6 patent gazette]
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]
B09B Patent application refused [chapter 9.2 patent gazette]