CN106068519B - 用于共用神经元模型的高效实现的方法和装置 - Google Patents

用于共用神经元模型的高效实现的方法和装置 Download PDF

Info

Publication number
CN106068519B
CN106068519B CN201580010482.1A CN201580010482A CN106068519B CN 106068519 B CN106068519 B CN 106068519B CN 201580010482 A CN201580010482 A CN 201580010482A CN 106068519 B CN106068519 B CN 106068519B
Authority
CN
China
Prior art keywords
neuron model
neuron
instances
memory
state variables
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
CN201580010482.1A
Other languages
English (en)
Chinese (zh)
Other versions
CN106068519A (zh
Inventor
A·莎拉
J·A·莱文
J·B·格尔哈尔
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 CN106068519A publication Critical patent/CN106068519A/zh
Application granted granted Critical
Publication of CN106068519B publication Critical patent/CN106068519B/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
    • 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
    • G06N3/10—Interfaces, programming languages or software development kits, e.g. for simulating neural 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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of 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
    • G06N3/04—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
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Artificial Intelligence (AREA)
  • Neurology (AREA)
  • Image Analysis (AREA)
  • Semiconductor Memories (AREA)
  • User Interface Of Digital Computer (AREA)
  • Stored Programmes (AREA)
CN201580010482.1A 2014-02-28 2015-02-12 用于共用神经元模型的高效实现的方法和装置 Active CN106068519B (zh)

Applications Claiming Priority (5)

Application Number Priority Date Filing Date Title
US201461946051P 2014-02-28 2014-02-28
US61/946,051 2014-02-28
US14/267,394 US9672464B2 (en) 2014-02-28 2014-05-01 Method and apparatus for efficient implementation of common neuron models
US14/267,394 2014-05-01
PCT/US2015/015637 WO2015130476A2 (en) 2014-02-28 2015-02-12 Method and apparatus for efficient implementation of common neuron models

Publications (2)

Publication Number Publication Date
CN106068519A CN106068519A (zh) 2016-11-02
CN106068519B true CN106068519B (zh) 2018-12-18

Family

ID=54006937

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201580010482.1A Active CN106068519B (zh) 2014-02-28 2015-02-12 用于共用神经元模型的高效实现的方法和装置

Country Status (7)

Country Link
US (1) US9672464B2 (enExample)
EP (1) EP3111378A2 (enExample)
JP (1) JP2017510890A (enExample)
KR (1) KR20160125967A (enExample)
CN (1) CN106068519B (enExample)
CA (1) CA2937945A1 (enExample)
WO (1) WO2015130476A2 (enExample)

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10068170B2 (en) * 2013-09-23 2018-09-04 Oracle International Corporation Minimizing global error in an artificial neural network
KR102372423B1 (ko) * 2017-05-16 2022-03-10 한국전자통신연구원 파라미터 공유 장치 및 방법
US11507806B2 (en) * 2017-09-08 2022-11-22 Rohit Seth Parallel neural processor for Artificial Intelligence
US11195079B2 (en) * 2017-11-22 2021-12-07 Intel Corporation Reconfigurable neuro-synaptic cores for spiking neural network
US11347998B2 (en) * 2018-02-26 2022-05-31 Fredric William Narcross Nervous system on a chip
CN108830379B (zh) * 2018-05-23 2021-12-17 电子科技大学 一种基于参数量化共享的神经形态处理器
CN109886384B (zh) * 2019-02-15 2021-01-05 北京工业大学 一种基于鼠脑海马网格细胞重构的仿生导航方法
US11270195B2 (en) 2019-03-05 2022-03-08 International Business Machines Corporation Neuromorphic computing in dynamic random access memory
WO2021137601A1 (ko) * 2019-12-30 2021-07-08 매니코어소프트주식회사 강화 학습 기반의 프로그램 최적화 방법

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5615306A (en) * 1990-02-20 1997-03-25 International Business Machines Corporation Neural network shell for application programs
CN1333518A (zh) * 2000-07-13 2002-01-30 国际商业机器公司 用于将范数与提供给神经网络的输入模型的每个分量相关联的方法和电路

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH05128083A (ja) * 1991-10-31 1993-05-25 Ricoh Co Ltd 信号処理装置
US6167390A (en) * 1993-12-08 2000-12-26 3M Innovative Properties Company Facet classification neural network
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
US8027942B2 (en) * 2000-12-13 2011-09-27 International Business Machines Corporation Method and circuits for associating a complex operator to each component of an input pattern presented to an artificial neural network
JP4710931B2 (ja) 2008-07-09 2011-06-29 ソニー株式会社 学習装置、学習方法、およびプログラム
US8655815B2 (en) 2010-05-19 2014-02-18 The Regents Of The University Of California Neural processing unit
US8650008B2 (en) 2010-08-05 2014-02-11 International Business Machines Corporation Method and system of developing corner models for various classes on nonlinear systems
KR101888468B1 (ko) 2011-06-08 2018-08-16 삼성전자주식회사 Ｓｔｄｐ 기능 셀을 위한 시냅스, ｓｔｄｐ 기능 셀 및 ｓｔｄｐ 기능 셀을 이용한 뉴로모픽 회로
US9111224B2 (en) * 2011-10-19 2015-08-18 Qualcomm Incorporated Method and apparatus for neural learning of natural multi-spike trains in spiking neural networks
US9111225B2 (en) * 2012-02-08 2015-08-18 Qualcomm Incorporated Methods and apparatus for spiking neural computation
US9256215B2 (en) 2012-07-27 2016-02-09 Brain Corporation Apparatus and methods for generalized state-dependent learning in spiking neuron networks
US9256823B2 (en) 2012-07-27 2016-02-09 Qualcomm Technologies Inc. Apparatus and methods for efficient updates in spiking neuron network

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5615306A (en) * 1990-02-20 1997-03-25 International Business Machines Corporation Neural network shell for application programs
CN1333518A (zh) * 2000-07-13 2002-01-30 国际商业机器公司 用于将范数与提供给神经网络的输入模型的每个分量相关联的方法和电路

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
A LARGE-SCALE SPIKING NEURAL NETWORK ACCELERATOR FOR FPGA SYSTEMS;Kit Cheung等;《LECTURE NOTES IN COMPUTER SCIENCE》;20120911;摘要、第1-3节，图1 *

Also Published As

Publication number Publication date
KR20160125967A (ko) 2016-11-01
EP3111378A2 (en) 2017-01-04
US20150248607A1 (en) 2015-09-03
CN106068519A (zh) 2016-11-02
US9672464B2 (en) 2017-06-06
JP2017510890A (ja) 2017-04-13
CA2937945A1 (en) 2015-09-03
WO2015130476A2 (en) 2015-09-03
WO2015130476A3 (en) 2015-10-22

Similar Documents

Publication Publication Date Title
CN106068519B (zh) 用于共用神经元模型的高效实现的方法和装置
CN105229675B (zh) 尖峰网络的高效硬件实现
CN105637541B (zh) 用于神经模拟器的共享存储器架构
CN106030622B (zh) 原位神经网络协同处理
US20150120627A1 (en) Causal saliency time inference
TWI585695B (zh) 用於定義多個神經元的動態的方法、設備及電腦可讀取媒體
EP3097516A1 (en) Configuring neural network for low spiking rate
CN105556543B (zh) 针对神经模型的群组标签的实现方案的方法和装置
WO2015020802A2 (en) Computed synapses for neuromorphic systems
TW201539335A (zh) 實現神經網路處理器
CN105659262A (zh) 在尖峰神经网络中使用重放来实现突触学习
CN106164940A (zh) 在尖峰神经网络中通过全局标量值来调制可塑性
US9542645B2 (en) Plastic synapse management
CN105659260B (zh) 动态地指派和检查突触延迟
WO2014197175A2 (en) Efficient implementation of neural population diversity in neural system
CN106030621B (zh) 用于空间目标选择的失衡式交叉抑制性机制
WO2015053908A2 (en) Method and apparatus to control and monitor neural model execution remotely

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