BR112017000229A2 - operação de convolução decomponível em redes neurais - Google Patents

operação de convolução decomponível em redes neurais

Info

Publication number
BR112017000229A2
BR112017000229A2 BR112017000229A BR112017000229A BR112017000229A2 BR 112017000229 A2 BR112017000229 A2 BR 112017000229A2 BR 112017000229 A BR112017000229 A BR 112017000229A BR 112017000229 A BR112017000229 A BR 112017000229A BR 112017000229 A2 BR112017000229 A2 BR 112017000229A2
Authority
BR
Brazil
Prior art keywords
neural networks
convolution operation
decomposable
decomposable convolution
neural network
Prior art date
Application number
BR112017000229A
Other languages
English (en)
Inventor
Sreekanta Reddy Annapureddy Venkata
Original Assignee
Qualcomm Inc
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 Qualcomm Inc filed Critical Qualcomm Inc
Publication of BR112017000229A2 publication Critical patent/BR112017000229A2/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
    • 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
    • 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
    • G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
    • 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
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Molecular Biology (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Image Analysis (AREA)
  • Electrically Operated Instructional Devices (AREA)

Abstract

trata-se de um método de treinamento de uma rede neural que inclui encorajar um ou mais filtros na rede neural a terem uma classificação baixa.
BR112017000229A 2014-07-16 2015-07-13 operação de convolução decomponível em redes neurais BR112017000229A2 (pt)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US201462025406P 2014-07-16 2014-07-16
US14/526,046 US10402720B2 (en) 2014-07-16 2014-10-28 Decomposing convolution operation in neural networks
PCT/US2015/040221 WO2016010930A1 (en) 2014-07-16 2015-07-13 Decomposing convolution operation in neural networks

Publications (1)

Publication Number Publication Date
BR112017000229A2 true BR112017000229A2 (pt) 2017-10-31

Family

ID=55074837

Family Applications (1)

Application Number Title Priority Date Filing Date
BR112017000229A BR112017000229A2 (pt) 2014-07-16 2015-07-13 operação de convolução decomponível em redes neurais

Country Status (8)

Country Link
US (2) US10402720B2 (pt)
EP (2) EP3170127A1 (pt)
JP (1) JP2017525038A (pt)
KR (1) KR20170031695A (pt)
CN (2) CN106537421A (pt)
AU (1) AU2015289877A1 (pt)
BR (1) BR112017000229A2 (pt)
WO (2) WO2016010930A1 (pt)

Families Citing this family (25)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10402720B2 (en) 2014-07-16 2019-09-03 Qualcomm Incorporated Decomposing convolution operation in neural networks
US10262259B2 (en) * 2015-05-08 2019-04-16 Qualcomm Incorporated Bit width selection for fixed point neural networks
US10713562B2 (en) * 2016-06-18 2020-07-14 International Business Machines Corporation Neuromorphic memory circuit
CN106326985A (zh) * 2016-08-18 2017-01-11 北京旷视科技有限公司 神经网络训练方法和装置及数据处理方法和装置
US11238337B2 (en) * 2016-08-22 2022-02-01 Applied Brain Research Inc. Methods and systems for implementing dynamic neural networks
EP3306535B1 (en) * 2016-10-10 2019-12-04 Alcatel Lucent Runtime optimization of convolutional neural networks
KR20180073118A (ko) * 2016-12-22 2018-07-02 삼성전자주식회사 컨볼루션 신경망 처리 방법 및 장치
US11301750B2 (en) 2017-03-31 2022-04-12 Ecole Polytechnique Federale De Lausanne (Epfl) Simplification of neural models that include arborized projections
DE102017205713A1 (de) 2017-04-04 2018-10-04 Siemens Aktiengesellschaft Verfahren und Steuereinrichtung zum Steuern eines technischen Systems
US11037330B2 (en) 2017-04-08 2021-06-15 Intel Corporation Low rank matrix compression
CN107248144B (zh) * 2017-04-27 2019-12-10 东南大学 一种基于压缩型卷积神经网络的图像去噪方法
US11093832B2 (en) 2017-10-19 2021-08-17 International Business Machines Corporation Pruning redundant neurons and kernels of deep convolutional neural networks
CN107729994B (zh) 2017-11-28 2020-05-26 南京地平线机器人技术有限公司 执行卷积神经网络中的卷积层的运算的方法和装置
WO2019146189A1 (ja) * 2018-01-29 2019-08-01 日本電気株式会社 ニューラルネットワークのランク最適化装置および最適化方法
US11238346B2 (en) * 2018-04-25 2022-02-01 Qualcomm Incorproated Learning a truncation rank of singular value decomposed matrices representing weight tensors in neural networks
JP7021010B2 (ja) * 2018-06-06 2022-02-16 株式会社Ｎｔｔドコモ 機械学習システム
US11922314B1 (en) * 2018-11-30 2024-03-05 Ansys, Inc. Systems and methods for building dynamic reduced order physical models
CN109948787B (zh) * 2019-02-26 2021-01-08 山东师范大学 用于神经网络卷积层的运算装置、芯片及方法
US11580399B2 (en) 2019-04-30 2023-02-14 Samsung Electronics Co., Ltd. System and method for convolutional layer structure for neural networks
WO2020235011A1 (ja) * 2019-05-21 2020-11-26 日本電信電話株式会社 学習装置、学習方法及び学習プログラム
CN112215329B (zh) * 2019-07-09 2023-09-29 杭州海康威视数字技术股份有限公司 基于神经网络的卷积计算方法及装置
CN112784207B (zh) * 2019-11-01 2024-02-02 中科寒武纪科技股份有限公司 运算方法及相关产品
US11010691B1 (en) * 2020-03-16 2021-05-18 Sas Institute Inc. Distributable event prediction and machine learning recognition system
KR102427737B1 (ko) 2020-09-18 2022-08-01 네이버 주식회사 표현적 병목 현상이 최소화된 인공 신경망을 기반으로 하는 전자 장치 및 그의 동작 방법
US20230057387A1 (en) * 2021-07-23 2023-02-23 Cohere Inc. System and Method for Low Rank Training of Neural Networks

Family Cites Families (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5781700A (en) * 1996-02-05 1998-07-14 Ford Global Technologies, Inc. Trained Neural network air/fuel control system
US6351740B1 (en) * 1997-12-01 2002-02-26 The Board Of Trustees Of The Leland Stanford Junior University Method and system for training dynamic nonlinear adaptive filters which have embedded memory
US6269351B1 (en) * 1999-03-31 2001-07-31 Dryken Technologies, Inc. Method and system for training an artificial neural network
US6754380B1 (en) * 2003-02-14 2004-06-22 The University Of Chicago Method of training massive training artificial neural networks (MTANN) for the detection of abnormalities in medical images
US7706992B2 (en) 2005-02-23 2010-04-27 Digital Intelligence, L.L.C. System and method for signal decomposition, analysis and reconstruction
ITRM20050192A1 (it) 2005-04-20 2006-10-21 Consiglio Nazionale Ricerche Sistema per la rilevazione e la classificazione di eventi durante azioni in movimento.
US7945061B1 (en) 2006-06-07 2011-05-17 Bae Systems Information And Electronic Systems Integration Inc. Scalable architecture for subspace signal tracking
JP5315411B2 (ja) 2008-07-03 2013-10-16 エヌイーシー ラボラトリーズ アメリカ インク 有糸分裂像検出装置および計数システム、および有糸分裂像を検出して計数する方法
CN101667425A (zh) 2009-09-22 2010-03-10 山东大学 一种对卷积混叠语音信号进行盲源分离的方法
BRPI0904540B1 (pt) 2009-11-27 2021-01-26 Samsung Eletrônica Da Amazônia Ltda método para animar rostos/cabeças/personagens virtuais via processamento de voz
US8874432B2 (en) 2010-04-28 2014-10-28 Nec Laboratories America, Inc. Systems and methods for semi-supervised relationship extraction
US8583586B2 (en) 2011-01-21 2013-11-12 International Business Machines Corporation Mining temporal patterns in longitudinal event data using discrete event matrices and sparse coding
US9262724B2 (en) 2012-07-13 2016-02-16 International Business Machines Corporation Low-rank matrix factorization for deep belief network training with high-dimensional output targets
CN102820653B (zh) 2012-09-12 2014-07-30 湖南大学 一种电能质量综合控制器模糊-神经网络双闭环控制方法
US20140156575A1 (en) 2012-11-30 2014-06-05 Nuance Communications, Inc. Method and Apparatus of Processing Data Using Deep Belief Networks Employing Low-Rank Matrix Factorization
CN103325382A (zh) 2013-06-07 2013-09-25 大连民族学院 一种自动识别中国少数民族传统乐器音频数据的方法
US9728184B2 (en) 2013-06-18 2017-08-08 Microsoft Technology Licensing, Llc Restructuring deep neural network acoustic models
US9400955B2 (en) * 2013-12-13 2016-07-26 Amazon Technologies, Inc. Reducing dynamic range of low-rank decomposition matrices
US10402720B2 (en) 2014-07-16 2019-09-03 Qualcomm Incorporated Decomposing convolution operation in neural networks

Also Published As

Publication number Publication date
US10402720B2 (en) 2019-09-03
WO2016010922A1 (en) 2016-01-21
US20160019456A1 (en) 2016-01-21
US20160019455A1 (en) 2016-01-21
US10360497B2 (en) 2019-07-23
CN106663222A (zh) 2017-05-10
CN106537421A (zh) 2017-03-22
KR20170031695A (ko) 2017-03-21
JP2017525038A (ja) 2017-08-31
WO2016010930A1 (en) 2016-01-21
AU2015289877A1 (en) 2017-01-05
EP3170127A1 (en) 2017-05-24
EP3170126A1 (en) 2017-05-24

Similar Documents

Publication Publication Date Title
BR112017000229A2 (pt) operação de convolução decomponível em redes neurais
CL2020000060A1 (es) Compuestos antiproliferativos y métodos para utilizarlos.
IL257579A (en) Near real-time modeling of pollution dispersion
DK3359172T3 (da) Sammensætninger omfattende bakteriestammer
GB201805522D0 (en) Natural language interface to databases
IL251708A0 (en) Social ratings for network components
IL247533A0 (en) A neural network and a method for training a neural network
CL2016000839A1 (es) Composiciones para modular la expresión de c9orf72.
DK3137605T3 (da) Sammensætninger og fremgangsmåder til modulering af angiopoietin-lignende-3-ekspression
IL255615A (en) Use of cannabis to treat fibromyalgia, methods and compositions thereof
BR112016022871A2 (pt) “equipamento e método para polarizador de guia de onda que compreende uma série de curvas”
CL2016002764A1 (es) Composiciones y métodos para modular la expresión del factor b del complemento
BR112017018620A2 (pt) método de administração de tradipitanto, e, tradipitanto.
MA39911A (fr) Polyoléfines lubrifiantes de basse viscosité
BR112017028013A2 (pt) indução de células t regulatórias da lâmina própria
MA45857A (fr) Composés et compositions, et utilisations associées
DK3233071T3 (da) Fremgangsmåde til behandling eller forebyggelse af Ras-medierede sygdomme
KR20180084794A (ko) 외과 수술 시뮬레이터 및 외과 수술 시뮬레이션 방법
DK3073409T3 (da) Maskering af forskellige indholdstyper
DK3903182T3 (da) Naturligt løsningssprog
MA45795A (fr) Composés et compositions, et utilisations associées
DK3230215T3 (da) Afvandningsoptimering i realtid
DE112016003101A5 (de) Demonstrator zur Simulation von Tageslicht
MA53889A (fr) Prothèse ligamentaire
IT201700078538A1 (it) Gestore domiciliare rifiuti differenziati (gdrd)

Legal Events

Date Code Title Description
B06U Preliminary requirement: requests with searches performed by other patent offices: procedure suspended [chapter 6.21 patent gazette]
B08F Application fees: application dismissed [chapter 8.6 patent gazette]

Free format text: REFERENTE A 5A ANUIDADE.

B11B Dismissal acc. art. 36, par 1 of ipl - no reply within 90 days to fullfil the necessary requirements