JP2016501398A - 区分的線形ニューロンモデル化 - Google Patents

区分的線形ニューロンモデル化 Download PDF

Info

Publication number
JP2016501398A
JP2016501398A JP2015542690A JP2015542690A JP2016501398A JP 2016501398 A JP2016501398 A JP 2016501398A JP 2015542690 A JP2015542690 A JP 2015542690A JP 2015542690 A JP2015542690 A JP 2015542690A JP 2016501398 A JP2016501398 A JP 2016501398A
Authority
JP
Japan
Prior art keywords
neuron
model
parameters
state
processing unit
Prior art date
Legal status (The legal status 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 status listed.)
Pending
Application number
JP2015542690A
Other languages
English (en)
Japanese (ja)
Other versions
JP2016501398A5 (enExample
Inventor
パドバニ、ロバート
ヨン、ユン・チュル
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Qualcomm Inc
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 JP2016501398A publication Critical patent/JP2016501398A/ja
Publication of JP2016501398A5 publication Critical patent/JP2016501398A5/ja
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; 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 OR CALCULATING; 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 OR CALCULATING; 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
    • G06N3/0499—Feedforward networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
    • G06N3/063—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Image Analysis (AREA)
JP2015542690A 2012-11-20 2013-11-05 区分的線形ニューロンモデル化 Pending JP2016501398A (ja)

Applications Claiming Priority (11)

Application Number Priority Date Filing Date Title
US201261728360P 2012-11-20 2012-11-20
US61/728,360 2012-11-20
US201261734716P 2012-12-07 2012-12-07
US61/734,716 2012-12-07
US201261740633P 2012-12-21 2012-12-21
US61/740,633 2012-12-21
US201361756889P 2013-01-25 2013-01-25
US61/756,889 2013-01-25
US14/070,659 2013-11-04
US14/070,659 US20140143191A1 (en) 2012-11-20 2013-11-04 Piecewise linear neuron modeling
PCT/US2013/068531 WO2014081561A1 (en) 2012-11-20 2013-11-05 Piecewise linear neuron modeling

Publications (2)

Publication Number Publication Date
JP2016501398A true JP2016501398A (ja) 2016-01-18
JP2016501398A5 JP2016501398A5 (enExample) 2016-12-01

Family

ID=50728915

Family Applications (3)

Application Number Title Priority Date Filing Date
JP2015542690A Pending JP2016501398A (ja) 2012-11-20 2013-11-05 区分的線形ニューロンモデル化
JP2015542691A Active JP6117369B2 (ja) 2012-11-20 2013-11-05 区分的線形ニューロンモデル化
JP2015542689A Expired - Fee Related JP5976948B2 (ja) 2012-11-20 2013-11-05 区分的線形ニューロンモデル化

Family Applications After (2)

Application Number Title Priority Date Filing Date
JP2015542691A Active JP6117369B2 (ja) 2012-11-20 2013-11-05 区分的線形ニューロンモデル化
JP2015542689A Expired - Fee Related JP5976948B2 (ja) 2012-11-20 2013-11-05 区分的線形ニューロンモデル化

Country Status (7)

Country Link
US (3) US9477926B2 (enExample)
EP (3) EP2923310A1 (enExample)
JP (3) JP2016501398A (enExample)
KR (1) KR20150087266A (enExample)
CN (3) CN104798089B (enExample)
TW (3) TWI584207B (enExample)
WO (3) WO2014081562A1 (enExample)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019117646A1 (ko) * 2017-12-15 2019-06-20 한국전자통신연구원 분산 처리 환경에서의 학습 파라미터의 압축 및 전송을 제공하는 방법 및 장치
KR20190072450A (ko) * 2017-12-15 2019-06-25 한국전자통신연구원 분산 처리 환경에서의 학습 파라미터의 압축 및 전송을 제공하는 방법 및 장치
KR20200104959A (ko) * 2019-02-27 2020-09-07 한국전력공사 분산 딥러닝 환경에서 데이터 압축 장치 및 방법

Families Citing this family (46)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9477926B2 (en) 2012-11-20 2016-10-25 Qualcomm Incorporated Piecewise linear neuron modeling
US10132529B2 (en) 2013-03-14 2018-11-20 Rolls-Royce Corporation Thermal management system controlling dynamic and steady state thermal loads
US10288325B2 (en) 2013-03-14 2019-05-14 Rolls-Royce Corporation Trans-critical vapor cycle system with improved heat rejection
US10068170B2 (en) * 2013-09-23 2018-09-04 Oracle International Corporation Minimizing global error in an artificial neural network
US20150324690A1 (en) * 2014-05-08 2015-11-12 Microsoft Corporation Deep Learning Training System
WO2016054441A1 (en) * 2014-10-01 2016-04-07 Thalchemy Corporation Efficient and scalable systems for calculating neural network connectivity in an event-driven way
KR20170074234A (ko) * 2014-10-23 2017-06-29 휴렛 팩커드 엔터프라이즈 디벨롭먼트 엘피 내적을 결정하기 위한 멤리스티브 크로스바 어레이
EP3214584A4 (en) * 2014-10-28 2018-07-25 Nec Corporation Region linear model optimization system, method, and program
US9747546B2 (en) * 2015-05-21 2017-08-29 Google Inc. Neural network processor
CN106528047B (zh) * 2015-10-08 2019-04-09 上海兆芯集成电路有限公司 一种处理器、神经网络单元及其运作方法
WO2017139342A1 (en) * 2016-02-08 2017-08-17 Spero Devices, Inc. Analog co-processor
JP6713164B2 (ja) * 2016-03-03 2020-06-24 国立研究開発法人物質・材料研究機構 シグナル解析方法及び試料ガス識別方法
US9990196B2 (en) * 2016-04-01 2018-06-05 Intel Corporation Instruction, circuits, and logic for piecewise linear approximation
CN106250600A (zh) * 2016-07-27 2016-12-21 上海华虹宏力半导体制造有限公司 提高mos器件模拟应用模型精准性的方法
US11270193B2 (en) 2016-09-30 2022-03-08 International Business Machines Corporation Scalable stream synaptic supercomputer for extreme throughput neural networks
US10679118B2 (en) * 2016-12-20 2020-06-09 Intel Corporation Solving matrix inverse problems using neuromorphic computing
CN106897734A (zh) * 2017-01-12 2017-06-27 南京大学 基于深度卷积神经网络的层内非均匀的k平均聚类定点量化方法
CN106875004B (zh) * 2017-01-20 2019-09-10 北京灵汐科技有限公司 复合模式神经元信息处理方法和系统
US10585703B2 (en) 2017-06-03 2020-03-10 Apple Inc. Dynamic operation allocation for neural networks
US20200250515A1 (en) * 2017-10-27 2020-08-06 Google Llc Systems and Methods for Improved Optimization of Machine-Learned Models
CN109960673B (zh) * 2017-12-14 2020-02-18 中科寒武纪科技股份有限公司 集成电路芯片装置及相关产品
KR102778395B1 (ko) * 2018-03-05 2025-03-11 한국전자통신연구원 심층신경망 모델의 선형 근사화 방법 및 장치
CN108647808B (zh) * 2018-04-11 2022-03-29 济南大学 一种生产参数优化预测方法、装置、设备及存储介质
US10489482B1 (en) * 2018-06-01 2019-11-26 Hewlett Packard Enterprise Development Lp Gaussian elimination via a vector matrix multiplication accelerator
US11468338B2 (en) 2018-09-11 2022-10-11 Apple Inc. Compiling models for dedicated hardware
US12020168B2 (en) * 2018-09-11 2024-06-25 Apple Inc. Compiling models for dedicated hardware
US11610110B2 (en) 2018-12-05 2023-03-21 Bank Of America Corporation De-conflicting data labeling in real time deep learning systems
CN109800851B (zh) * 2018-12-29 2024-03-01 中国人民解放军陆军工程大学 神经突触电路和脉冲神经网络电路
US11195085B2 (en) * 2019-03-21 2021-12-07 International Business Machines Corporation Spiking synaptic elements for spiking neural networks
CN110472733B (zh) * 2019-07-22 2023-05-02 天津大学 一种基于神经形态学的在体神经元建模方法
TWI728556B (zh) * 2019-11-18 2021-05-21 財團法人工業技術研究院 神經元電路及類神經網路晶片
KR102431371B1 (ko) * 2019-11-26 2022-08-10 성균관대학교산학협력단 스파이킹 뉴런 모델 및 그의 스파이크 생성 방법
TWI733305B (zh) * 2020-01-10 2021-07-11 瑞昱半導體股份有限公司 晶片及基於神經網路電路的電流調整方法
CN111241749B (zh) * 2020-01-13 2023-04-07 广西师范大学 一种基于储备池计算的永磁同步电动机混沌预测方法
CN111445017A (zh) * 2020-03-23 2020-07-24 天津芯海创科技有限公司 一种运算方法及装置
KR102339485B1 (ko) * 2020-06-30 2021-12-15 강원대학교산학협력단 인공신경망을 이용한 아크신호 검출방법
KR102883346B1 (ko) * 2020-09-09 2025-11-07 삼성전자주식회사 호스트 프로세서 및 가속기의 동작 방법 및 이들을 포함한 전자 장치
US11568255B2 (en) * 2020-09-10 2023-01-31 Mipsology SAS Fine tuning of trained artificial neural network
CN112966433B (zh) * 2021-02-08 2022-12-23 北京大学 一种基于即时编译的神经动力学仿真方法及装置
TW202248883A (zh) * 2021-05-31 2022-12-16 汎思數據股份有限公司 深度學習神經網路儲存與推論方法
KR102553119B1 (ko) 2021-12-01 2023-07-07 주식회사 딥엑스 프로그래밍 가능 활성화 함수 생성 방법 및 이를 이용하는 장치
US11836604B2 (en) 2021-12-01 2023-12-05 Deepx Co., Ltd. Method for generating programmable activation function and apparatus using the same
CN114861864B (zh) * 2022-02-24 2024-07-30 天津大学 具有树突形态学的神经元网络建模方法及装置
CN114781608B (zh) * 2022-04-19 2023-06-20 安徽科技学院 一种基于数字孪生的煤矿供电系统故障预警方法
CN116307942B (zh) * 2023-05-18 2023-08-25 中国人民解放军96901部队 基于指标影响力演化的联合作战效能评估方法、系统
CN118940682B (zh) * 2024-10-14 2025-02-07 芯瑞微(上海)电子科技有限公司 一种非均匀时间步长的热电路仿真方法及相关设备

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH08180034A (ja) * 1994-12-20 1996-07-12 Hitachi Microcomput Syst Ltd 情報処理装置
JPH1086447A (ja) * 1996-09-09 1998-04-07 Xerox Corp 静電写真プリントマシン
JP2002358094A (ja) * 2001-03-29 2002-12-13 Ricoh Co Ltd 音声認識システム
JP2005523534A (ja) * 2002-04-19 2005-08-04 コンピュータ アソシエイツ シンク，インコーポレイテッド 自動的ニューラルネットモデル発生及びメインテナンス
JP2010266975A (ja) * 2009-05-13 2010-11-25 Sony Corp 学習装置、学習方法、データ生成装置、データ生成方法、及び、プログラム
JP2011059815A (ja) * 2009-09-07 2011-03-24 Sony Corp 情報処理装置、情報処理方法、及び、プログラム
JP2012118718A (ja) * 2010-11-30 2012-06-21 Internatl Business Mach Corp <Ibm> スライディング・モード制御方式において、制御器を構成する方法、プログラム及びシステム

Family Cites Families (29)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4979126A (en) * 1988-03-30 1990-12-18 Ai Ware Incorporated Neural network with non-linear transformations
US5140670A (en) 1989-10-05 1992-08-18 Regents Of The University Of California Cellular neural network
GB2236608B (en) 1989-10-06 1993-08-18 British Telecomm Digital neural networks
DE4131765A1 (de) * 1991-09-24 1993-03-25 Siemens Ag Regelparameter-verbesserungsverfahren fuer industrielle anlagen
FR2685109A1 (fr) 1991-12-11 1993-06-18 Philips Electronique Lab Processeur numerique neuronal operant avec une approximation d'une fonction d'activation non lineaire.
KR970008532B1 (ko) 1993-08-10 1997-05-24 재단법인 한국전자통신연구소 비선형 함수의 근사를 위한 비선형 추정망의 학습방법
JPH0784974A (ja) 1993-09-16 1995-03-31 Nissan Motor Co Ltd リカレント・ニューラルネットワーク
KR100194761B1 (ko) 1996-10-02 1999-06-15 이계철 제어형 연속 램프(r므ㅔ) 변환기
US20050239737A1 (en) * 1998-05-12 2005-10-27 Isis Pharmaceuticals, Inc. Identification of molecular interaction sites in RNA for novel drug discovery
US6507828B1 (en) 1998-06-19 2003-01-14 Jason Leonard Neuron circuit and related techniques
US6728690B1 (en) * 1999-11-23 2004-04-27 Microsoft Corporation Classification system trainer employing maximum margin back-propagation with probabilistic outputs
EP1172763A3 (en) 2000-07-13 2008-11-05 International Business Machines Corporation Method and circuits for associating a norm to each component of an input pattern presented to a neural network
US6823322B2 (en) 2001-02-14 2004-11-23 Denso Corporation Piecewise nonlinear mapper for digitals
CN1417742A (zh) * 2002-12-16 2003-05-14 武汉大学 一种动态认知神经网络及实现方法
EP1515270A1 (en) * 2003-09-09 2005-03-16 Semeion An artificial neural network
US7647213B1 (en) * 2003-10-02 2010-01-12 The Mathworks, Inc. Method for modeling and analyzing linear time invariant systems with time delays
FR2881857B1 (fr) * 2005-02-04 2008-05-23 Bernard Angeniol Outil informatique de prevision
US7711663B2 (en) * 2006-03-27 2010-05-04 Board Of Trustees Of Michigan State University Multi-layer development network having in-place learning
TW200914844A (en) 2007-09-20 2009-04-01 Univ Far East Detection system and detection method for analyzing electronic signal state
CN101546389A (zh) 2008-03-26 2009-09-30 中国科学院半导体研究所 一种主方向神经网络系统
US8411910B2 (en) * 2008-04-17 2013-04-02 Biometricore, Inc. Computationally efficient feature extraction and matching iris recognition
TWI417798B (zh) 2008-11-21 2013-12-01 Nat Taipei University Oftechnology High - speed reverse transfer neural network system with elastic structure and learning function
TWI417797B (zh) 2010-02-04 2013-12-01 Univ Nat Taipei Technology A Parallel Learning Architecture and Its Method for Transferred Neural Network
CN101782743A (zh) 2010-02-11 2010-07-21 浙江大学 神经网络建模方法及系统
US8655815B2 (en) 2010-05-19 2014-02-18 The Regents Of The University Of California Neural processing unit
TW201145057A (en) 2010-06-02 2011-12-16 Chun-Chen Liu MLPR: a multilayer perceptron-based model reduction algorithm for nonlinear circuits
TWI467520B (zh) 2010-11-10 2015-01-01 Univ Nat Chiao Tung 建構個人化神經刺激模型之系統及方法
US9367797B2 (en) * 2012-02-08 2016-06-14 Jason Frank Hunzinger Methods and apparatus for spiking neural computation
US9477926B2 (en) * 2012-11-20 2016-10-25 Qualcomm Incorporated Piecewise linear neuron modeling

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH08180034A (ja) * 1994-12-20 1996-07-12 Hitachi Microcomput Syst Ltd 情報処理装置
JPH1086447A (ja) * 1996-09-09 1998-04-07 Xerox Corp 静電写真プリントマシン
JP2002358094A (ja) * 2001-03-29 2002-12-13 Ricoh Co Ltd 音声認識システム
JP2005523534A (ja) * 2002-04-19 2005-08-04 コンピュータ アソシエイツ シンク，インコーポレイテッド 自動的ニューラルネットモデル発生及びメインテナンス
JP2010266975A (ja) * 2009-05-13 2010-11-25 Sony Corp 学習装置、学習方法、データ生成装置、データ生成方法、及び、プログラム
JP2011059815A (ja) * 2009-09-07 2011-03-24 Sony Corp 情報処理装置、情報処理方法、及び、プログラム
JP2012118718A (ja) * 2010-11-30 2012-06-21 Internatl Business Mach Corp <Ibm> スライディング・モード制御方式において、制御器を構成する方法、プログラム及びシステム

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019117646A1 (ko) * 2017-12-15 2019-06-20 한국전자통신연구원 분산 처리 환경에서의 학습 파라미터의 압축 및 전송을 제공하는 방법 및 장치
KR20190072450A (ko) * 2017-12-15 2019-06-25 한국전자통신연구원 분산 처리 환경에서의 학습 파라미터의 압축 및 전송을 제공하는 방법 및 장치
KR102435595B1 (ko) 2017-12-15 2022-08-25 한국전자통신연구원 분산 처리 환경에서의 학습 파라미터의 압축 및 전송을 제공하는 방법 및 장치
US11663476B2 (en) 2017-12-15 2023-05-30 Electronics And Telecommunications Research Institute Method and device for providing compression and transmission of training parameters in distributed processing environment
KR20200104959A (ko) * 2019-02-27 2020-09-07 한국전력공사 분산 딥러닝 환경에서 데이터 압축 장치 및 방법
KR102425039B1 (ko) 2019-02-27 2022-07-28 한국전력공사 분산 딥러닝 환경에서 데이터 압축 장치 및 방법

Also Published As

Publication number Publication date
TWI537843B (zh) 2016-06-11
TWI541736B (zh) 2016-07-11
CN104781836A (zh) 2015-07-15
EP2923309A1 (en) 2015-09-30
EP2923310A1 (en) 2015-09-30
US20140143194A1 (en) 2014-05-22
TW201421381A (zh) 2014-06-01
US20140143191A1 (en) 2014-05-22
WO2014081562A1 (en) 2014-05-30
CN104798088A (zh) 2015-07-22
WO2014081560A1 (en) 2014-05-30
CN104798089A (zh) 2015-07-22
CN104798089B (zh) 2018-01-16
US9477926B2 (en) 2016-10-25
TW201421382A (zh) 2014-06-01
KR20150087266A (ko) 2015-07-29
CN104798088B (zh) 2018-02-23
TW201421383A (zh) 2014-06-01
JP2016501399A (ja) 2016-01-18
WO2014081561A1 (en) 2014-05-30
US20140143190A1 (en) 2014-05-22
EP2923308A1 (en) 2015-09-30
JP5976948B2 (ja) 2016-08-24
JP2016501397A (ja) 2016-01-18
US9292790B2 (en) 2016-03-22
JP6117369B2 (ja) 2017-04-19
TWI584207B (zh) 2017-05-21
CN104781836B (zh) 2018-05-08

Similar Documents

Publication Publication Date Title
JP6117369B2 (ja) 区分的線形ニューロンモデル化
US9542643B2 (en) Efficient hardware implementation of spiking networks
JP6092477B2 (ja) ニューラルダイナミクスを修正するための自動化された方法
US9600762B2 (en) Defining dynamics of multiple neurons
US20150046381A1 (en) Implementing delays between neurons in an artificial nervous system
US20150112909A1 (en) Congestion avoidance in networks of spiking neurons
US9460384B2 (en) Effecting modulation by global scalar values in a spiking neural network
US9542645B2 (en) Plastic synapse management
US9342782B2 (en) Stochastic delay plasticity
CA2926034A1 (en) Dynamically assigning and examining synaptic delay

Legal Events

Date Code Title Description
A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20161011

A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20161011

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20170919

A601 Written request for extension of time

Free format text: JAPANESE INTERMEDIATE CODE: A601

Effective date: 20171219

A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20180105

A02 Decision of refusal

Free format text: JAPANESE INTERMEDIATE CODE: A02

Effective date: 20180327