WO2009044751A1 - ニューロン装置、神経回路網装置、フィードバック制御装置、ならびに、情報記録媒体 - Google Patents

ニューロン装置、神経回路網装置、フィードバック制御装置、ならびに、情報記録媒体 Download PDF

Info

Publication number
WO2009044751A1
WO2009044751A1 PCT/JP2008/067774 JP2008067774W WO2009044751A1 WO 2009044751 A1 WO2009044751 A1 WO 2009044751A1 JP 2008067774 W JP2008067774 W JP 2008067774W WO 2009044751 A1 WO2009044751 A1 WO 2009044751A1
Authority
WO
WIPO (PCT)
Prior art keywords
thetav
threshold
neuron
neural network
value
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.)
Ceased
Application number
PCT/JP2008/067774
Other languages
English (en)
French (fr)
Inventor
Shingo Shimoda
Hidenori Kimura
Masaaki Yamaoka
Hideki Kajima
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.)
Toyota Motor Corp
RIKEN
Original Assignee
Toyota Motor Corp
RIKEN
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 Toyota Motor Corp, RIKEN filed Critical Toyota Motor Corp
Priority to US12/680,678 priority Critical patent/US8620844B2/en
Priority to CN2008801089833A priority patent/CN101809598B/zh
Publication of WO2009044751A1 publication Critical patent/WO2009044751A1/ja
Anticipated expiration legal-status Critical
Ceased 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
    • G06N3/06—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
    • 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
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00—Program-control systems
    • G05B2219/30—Nc systems
    • G05B2219/39—Robotics, robotics to robotics hand
    • G05B2219/39031—Use of model for robot and for measuring device

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • General Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Computational Linguistics (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Neurology (AREA)
  • Feedback Control In General (AREA)
  • Manipulator (AREA)

Abstract

　神経回路網においてニューロンの閾値を可変にし、ヘッブ則を拡張して、適切な制御を行うため、神経細胞をシミュレートするニューロン装置（１０１）において、閾値記憶部（１０２）は、閾値変数θと、２つの閾値係数Δθ1、Δθ2と、を記憶し、入力受付部（１０３）は、１つまたは複数の入力信号値の入力を、所定の時間間隔で受け付け、出力部（１０４）は、入力信号値の総和sが、閾値変数θの値以上であれば、ニューロン装置（１０１）が発火しているとして１を、そうでなければ、ニューロン装置（１０１）が休息しているとして０を、出力信号値Xとして出力し、閾値更新部（１０５）は、出力信号値Xと、閾値係数Δθ1、Δθ2と、からΔθ1 X + Δθ2(X - 1)を計算して、閾値記憶部（１０２）に記憶される閾値変数θの値をその計算結果だけ増加するように更新する。
PCT/JP2008/067774 2007-10-01 2008-09-30 ニューロン装置、神経回路網装置、フィードバック制御装置、ならびに、情報記録媒体 Ceased WO2009044751A1 (ja)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US12/680,678 US8620844B2 (en) 2007-10-01 2008-09-30 Neuron device for simulating a nerve cell and neural network device, integer cluster device, feedback control device, and computer program product thereof
CN2008801089833A CN101809598B (zh) 2007-10-01 2008-09-30 神经元装置、神经网络装置、反馈控制装置及信息存储介质

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2007-257123 2007-10-01
JP2007257123A JP5115965B2 (ja) 2007-10-01 2007-10-01 ニューロン装置、神経回路網装置、非負整数符号化装置、整数クラスタ装置、フィードバック制御装置、ならびに、プログラム

Publications (1)

Publication Number Publication Date
WO2009044751A1 true WO2009044751A1 (ja) 2009-04-09

Family

ID=40526178

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2008/067774 Ceased WO2009044751A1 (ja) 2007-10-01 2008-09-30 ニューロン装置、神経回路網装置、フィードバック制御装置、ならびに、情報記録媒体

Country Status (4)

Country Link
US (1) US8620844B2 (ja)
JP (1) JP5115965B2 (ja)
CN (1) CN101809598B (ja)
WO (1) WO2009044751A1 (ja)

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101980603B1 (ko) 2016-05-20 2019-05-22 구글 엘엘씨 오브젝트(들)를 캡처하는 이미지(들)에 기초하는 그리고 환경에서의 미래 로봇 움직임에 대한 파라미터(들)에 기초하여 로봇 환경에서의 오브젝트(들)의 모션(들)을 예측하는 것과 관련된 머신 학습 방법들 및 장치
CN114967433B (zh) * 2016-05-20 2023-08-18 谷歌有限责任公司 基于捕获物体的图像的机器学习方法和装置
WO2018113790A1 (zh) * 2016-12-23 2018-06-28 北京中科寒武纪科技有限公司 一种人工神经网络运算的装置及方法
CN107578097A (zh) * 2017-09-25 2018-01-12 胡明建 一种多阀值多函数反馈人工神经元的设计方法
US11995556B2 (en) 2018-05-18 2024-05-28 Cambricon Technologies Corporation Limited Video retrieval method, and method and apparatus for generating video retrieval mapping relationship
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
US11010132B2 (en) * 2018-09-28 2021-05-18 Tenstorrent Inc. Processing core with data associative adaptive rounding
CN111880406B (zh) * 2020-07-14 2022-04-15 金陵科技学院 基于Hebb学习的自适应预测控制主队列管理方法

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH05234009A (ja) * 1992-02-21 1993-09-10 Nec Corp サグ補償回路
JPH07141313A (ja) * 1993-11-18 1995-06-02 Fujitsu Ltd 神経回路素子
JPH07319507A (ja) * 1994-05-26 1995-12-08 Bridgestone Corp ロボット制御装置
WO2004104917A1 (ja) * 2003-05-20 2004-12-02 Fujitsu Limited センサおよびセンサプログラム

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4975961A (en) * 1987-10-28 1990-12-04 Nec Corporation Multi-layer neural network to which dynamic programming techniques are applicable
US4874963A (en) * 1988-02-11 1989-10-17 Bell Communications Research, Inc. Neuromorphic learning networks
US5446829A (en) * 1993-06-24 1995-08-29 The United States Of America As Represented By The Department Of Health And Human Services Artificial network for temporal sequence processing
JPH08249297A (ja) * 1995-03-15 1996-09-27 Toshiba Corp ニューラルネットワーク装置
JP3584669B2 (ja) * 1997-04-01 2004-11-04 トヨタ自動車株式会社 電気自動車用駆動制御装置
FR2912893B1 (fr) 2007-02-23 2009-12-11 Philippe Brunswick Systeme d'analyse electrophysiologique

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH05234009A (ja) * 1992-02-21 1993-09-10 Nec Corp サグ補償回路
JPH07141313A (ja) * 1993-11-18 1995-06-02 Fujitsu Ltd 神経回路素子
JPH07319507A (ja) * 1994-05-26 1995-12-08 Bridgestone Corp ロボット制御装置
WO2004104917A1 (ja) * 2003-05-20 2004-12-02 Fujitsu Limited センサおよびセンサプログラム

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
JUN SHIRAKURA: "Haba no Henka suru Kofunha ni yoru Yori Antei na Topographic Mapping Keisei Model", IEICE TECHNICAL REPORT, vol. 96, no. 117, 21 June 1996 (1996-06-21), pages 53 - 60 *

Also Published As

Publication number Publication date
US20100217733A1 (en) 2010-08-26
JP5115965B2 (ja) 2013-01-09
JP2009087114A (ja) 2009-04-23
CN101809598B (zh) 2013-06-19
CN101809598A (zh) 2010-08-18
US8620844B2 (en) 2013-12-31

Similar Documents

Publication Publication Date Title
WO2009044751A1 (ja) ニューロン装置、神経回路網装置、フィードバック制御装置、ならびに、情報記録媒体
Liu et al. Neural-network-based zero-sum game for discrete-time nonlinear systems via iterative adaptive dynamic programming algorithm
Yu Nonlinear system identification using discrete-time recurrent neural networks with stable learning algorithms
KR101683436B1 (ko) 신경 학습을 위한 방법, 장치 및 컴퓨터 판독가능 저장 매체
WO2008030990A3 (en) Adaptive and individual learning with feedback for online courses
WO2019010136A3 (en) DETERMINING AND USING CORRECTIONS FOR ROBOT ACTIONS
SG10201808441TA (en) Natural language processing artificial intelligence network and data security system
Rong et al. Adaptive fuzzy control of aircraft wing-rock motion
WO2008067396A3 (en) Adaptive cancellation system for implantable hearing instruments
WO2007053766A3 (en) Cooling components across a continuum
WO2009140024A3 (en) Gesture-related feedback in eletronic entertainment system
WO2008006772A3 (en) Method for operating a binaural hearing system as well as a binaural hearing system
Bhargawa et al. Solar irradiance, climatic indicators and climate change–An empirical analysis
WO2011102912A3 (en) Human-motion-training system
Sanford et al. Modeling integrated stress, sleep, fear and neuroimmune responses: Relevance for understanding trauma and stress-related disorders
WO2006044310A3 (en) Nonlinear system observation and control
Uzuntarla et al. Controlling the first-spike latency response of a single neuron via unreliable synaptic transmission
Ping Tracking problems of a spherical inverted pendulum via neural network enhanced design
CN112953458B (zh) 一种基于忆阻的二阶阻尼情感电路
KR20160022171A (ko) 슬라이딩 모드 제어장치
Wang et al. H∞ performance for a class of uncertain stochastic nonlinear Markovian jump systems with time-varying delay via adaptive control method
Chen et al. Fixed points and pth moment exponential stability of stochastic delayed recurrent neural networks with impulses
Alzabut et al. On existence of a globally attractive periodic solution of impulsive delay logarithmic population model
WO2007020456A3 (en) Neural network method and apparatus
Wears et al. Levels of resilience: moving from resilience to resilience engineering

Legal Events

Date Code Title Description
WWE Wipo information: entry into national phase

Ref document number: 200880108983.3

Country of ref document: CN

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 08836099

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 12680678

Country of ref document: US

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 08836099

Country of ref document: EP

Kind code of ref document: A1