CN103930908B - 无监督的神经重放、学习完善、关联以及记忆转移的方法和装置：神经组件重放 - Google Patents

无监督的神经重放、学习完善、关联以及记忆转移的方法和装置：神经组件重放 Download PDF

Info

Publication number
CN103930908B
CN103930908B CN201280055203.XA CN201280055203A CN103930908B CN 103930908 B CN103930908 B CN 103930908B CN 201280055203 A CN201280055203 A CN 201280055203A CN 103930908 B CN103930908 B CN 103930908B
Authority
CN
China
Prior art keywords
neuron
pattern
afferent
neurons
relation
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.)
Active
Application number
CN201280055203.XA
Other languages
English (en)
Chinese (zh)
Other versions
CN103930908A (zh
Inventor
J·F·亨泽格
V·H·陈
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 CN103930908A publication Critical patent/CN103930908A/zh
Application granted granted Critical
Publication of CN103930908B publication Critical patent/CN103930908B/zh
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G06N3/04—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
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/088—Non-supervised learning, e.g. competitive 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
    • G06N3/08—Learning methods
    • G06N3/092—Reinforcement learning

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Image Analysis (AREA)
  • User Interface Of Digital Computer (AREA)
  • Machine Translation (AREA)
  • Testing Of Coins (AREA)
  • Detergent Compositions (AREA)
  • Air Conditioning Control Device (AREA)
CN201280055203.XA 2011-11-09 2012-11-09 无监督的神经重放、学习完善、关联以及记忆转移的方法和装置：神经组件重放 Active CN103930908B (zh)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US13/292,167 2011-11-09
US13/292,167 US9424511B2 (en) 2011-11-09 2011-11-09 Methods and apparatus for unsupervised neural component replay by referencing a pattern in neuron outputs
PCT/US2012/064521 WO2013071164A1 (en) 2011-11-09 2012-11-09 Methods and apparatus for unsupervised neural replay, learning refinement, association and memory transfer: neural component replay

Publications (2)

Publication Number Publication Date
CN103930908A CN103930908A (zh) 2014-07-16
CN103930908B true CN103930908B (zh) 2017-06-27

Family

ID=47428967

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201280055203.XA Active CN103930908B (zh) 2011-11-09 2012-11-09 无监督的神经重放、学习完善、关联以及记忆转移的方法和装置：神经组件重放

Country Status (7)

Country Link
US (1) US9424511B2 (https=)
EP (1) EP2776987A1 (https=)
JP (1) JP5989793B2 (https=)
KR (1) KR101616660B1 (https=)
CN (1) CN103930908B (https=)
IN (1) IN2014CN03033A (https=)
WO (1) WO2013071164A1 (https=)

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9443190B2 (en) 2011-11-09 2016-09-13 Qualcomm Incorporated Methods and apparatus for neural pattern sequence completion and neural pattern hierarchical replay by invoking replay of a referenced neural pattern
US9424513B2 (en) 2011-11-09 2016-08-23 Qualcomm Incorporated Methods and apparatus for neural component memory transfer of a referenced pattern by including neurons to output a pattern substantially the same as the referenced pattern
US9015091B2 (en) * 2011-11-09 2015-04-21 Qualcomm Incorporated Methods and apparatus for unsupervised neural replay, learning refinement, association and memory transfer: structural plasticity and structural constraint modeling
US9652711B2 (en) 2014-03-12 2017-05-16 Qualcomm Incorporated Analog signal reconstruction and recognition via sub-threshold modulation
CN104778202B (zh) * 2015-02-05 2018-08-14 北京航空航天大学 基于关键词的事件演化过程的分析方法及系统
CN106650922B (zh) * 2016-09-29 2019-05-03 清华大学 硬件神经网络转换方法、计算装置、软硬件协作系统
CN109002647B (zh) * 2018-08-17 2019-06-07 郑州轻工业学院 一种具有延时学习功能的忆阻联想记忆神经网络电路
US11790245B2 (en) * 2019-01-22 2023-10-17 International Business Machines Corporation Cognitive machine learning for semantic network
WO2020210673A1 (en) * 2019-04-10 2020-10-15 Cornell University Neuromorphic algorithm for rapid online learning and signal restoration
CN110222387B (zh) * 2019-05-24 2021-01-12 北京化工大学 基于混合漏积分crj网络的多元钻井时间序列预测方法
US11742901B2 (en) * 2020-07-27 2023-08-29 Electronics And Telecommunications Research Institute Deep learning based beamforming method and apparatus

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1150847A (zh) * 1994-05-02 1997-05-28 摩托罗拉公司 使用神经网络的计算机和使用该神经网络的方法
WO2004097733A2 (en) * 2003-04-30 2004-11-11 Darwinian Neural Network Industries Ltd Neural networks
CN101809539A (zh) * 2007-08-06 2010-08-18 枢科技术有限责任公司 经由多个通过预定关系连接在一起的概念节点定义人造大脑的方法和装置

Family Cites Families (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7089218B1 (en) 2004-01-06 2006-08-08 Neuric Technologies, Llc Method for inclusion of psychological temperament in an electronic emulation of the human brain
JP3647584B2 (ja) 1996-12-26 2005-05-11 富士通株式会社 学習型自己定位装置
US6041322A (en) 1997-04-18 2000-03-21 Industrial Technology Research Institute Method and apparatus for processing data in a neural network
JP2005190429A (ja) 2003-12-26 2005-07-14 Hiroshima Univ 参照データ認識・学習方法及びパターン認識システム
EP2360629A3 (en) 2005-05-07 2012-04-11 Stephen L. Thaler Device for the autonomous bootstrapping of useful information
JP4201012B2 (ja) 2006-04-06 2008-12-24 ソニー株式会社 データ処理装置、データ処理方法、およびプログラム
EP2259214B1 (en) 2009-06-04 2013-02-27 Honda Research Institute Europe GmbH Implementing a neural associative memory based on non-linear learning of discrete synapses
US20120117012A1 (en) * 2010-04-08 2012-05-10 Neurosciences Research Foundation, Inc. Spike-timing computer modeling of working memory
WO2012138761A1 (en) * 2011-04-04 2012-10-11 Sheepdog Sciences, Inc. Apparatus, system, and method for modulating consolidation of memory during sleep
US9147155B2 (en) 2011-08-16 2015-09-29 Qualcomm Incorporated Method and apparatus for neural temporal coding, learning and recognition
US9443190B2 (en) 2011-11-09 2016-09-13 Qualcomm Incorporated Methods and apparatus for neural pattern sequence completion and neural pattern hierarchical replay by invoking replay of a referenced neural pattern
US9424513B2 (en) 2011-11-09 2016-08-23 Qualcomm Incorporated Methods and apparatus for neural component memory transfer of a referenced pattern by including neurons to output a pattern substantially the same as the referenced pattern
US9015091B2 (en) 2011-11-09 2015-04-21 Qualcomm Incorporated Methods and apparatus for unsupervised neural replay, learning refinement, association and memory transfer: structural plasticity and structural constraint modeling
US8909575B2 (en) 2012-02-29 2014-12-09 Qualcomm Incorporated Method and apparatus for modeling neural resource based synaptic placticity
WO2014081671A1 (en) 2012-11-20 2014-05-30 Qualcomm Incorporated Dynamical event neuron and synapse models for learning spiking neural networks

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1150847A (zh) * 1994-05-02 1997-05-28 摩托罗拉公司 使用神经网络的计算机和使用该神经网络的方法
WO2004097733A2 (en) * 2003-04-30 2004-11-11 Darwinian Neural Network Industries Ltd Neural networks
CN101809539A (zh) * 2007-08-06 2010-08-18 枢科技术有限责任公司 经由多个通过预定关系连接在一起的概念节点定义人造大脑的方法和装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
Discrete States of Synaptic Strength in a Stochastic Model of Spike-Timing-Dependent Plasticity;Terry Elliott etal;《Neural Computation》;20100131;第22卷(第1期);第244-267页 *

Also Published As

Publication number Publication date
CN103930908A (zh) 2014-07-16
US20130117210A1 (en) 2013-05-09
KR101616660B1 (ko) 2016-04-28
IN2014CN03033A (https=) 2015-07-03
EP2776987A1 (en) 2014-09-17
US9424511B2 (en) 2016-08-23
JP2014535119A (ja) 2014-12-25
KR20140092881A (ko) 2014-07-24
WO2013071164A1 (en) 2013-05-16
JP5989793B2 (ja) 2016-09-07

Similar Documents

Publication Publication Date Title
CN103930908B (zh) 无监督的神经重放、学习完善、关联以及记忆转移的方法和装置：神经组件重放
CN105868828B (zh) 神经系统工程设计方法和装置
KR101582061B1 (ko) 비감독 신경 리플레이, 학습 리파인먼트, 연관 및 기억 전달: 구조적 가소성 및 구조적 제약 모델링을 위한 방법들 및 장치
KR101755082B1 (ko) 신경 성분 기억 전달을 위한 방법, 장치 및 컴퓨터 판독가능 저장 매체
TW201426576A (zh) 用於設計湧現式多層尖峰網路的方法和裝置
US9652711B2 (en) Analog signal reconstruction and recognition via sub-threshold modulation
JP2017513127A (ja) スパイキング深層信念ネットワーク（ｄｂｎ）におけるトレーニング、認識、および生成
JP2017531240A (ja) データのナレッジグラフバイアス分類
Melchior et al. A neural network model for online one-shot storage of pattern sequences
Siddique Harnessing the Power of Voltage-dependent Synaptic Plasticity (VDSP): A Novel Paradigm for Unsupervised Learning in Neuromorphic Systems
CN116756387B (en) Time-awareness-based graph neural network session recommendation method and system

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant