CN105659260B - 动态地指派和检查突触延迟 - Google Patents

动态地指派和检查突触延迟 Download PDF

Info

Publication number
CN105659260B
CN105659260B CN201480056520.2A CN201480056520A CN105659260B CN 105659260 B CN105659260 B CN 105659260B CN 201480056520 A CN201480056520 A CN 201480056520A CN 105659260 B CN105659260 B CN 105659260B
Authority
CN
China
Prior art keywords
delay parameter
delay
dynamically
synaptic
neural network
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
CN201480056520.2A
Other languages
English (en)
Chinese (zh)
Other versions
CN105659260A (zh
Inventor
A·莎拉
R·H·金鲍尔
B·什皮纳尔
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 CN105659260A publication Critical patent/CN105659260A/zh
Application granted granted Critical
Publication of CN105659260B publication Critical patent/CN105659260B/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
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • 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
    • G06N3/047—Probabilistic or stochastic 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
    • G06N3/049—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
    • G06N3/10—Interfaces, programming languages or software development kits, e.g. for simulating neural networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Computational Linguistics (AREA)
  • Molecular Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Operations Research (AREA)
  • Algebra (AREA)
  • Databases & Information Systems (AREA)
  • Image Analysis (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
CN201480056520.2A 2013-10-17 2014-08-21 动态地指派和检查突触延迟 Active CN105659260B (zh)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US14/056,856 2013-10-17
US14/056,856 US9536190B2 (en) 2013-10-17 2013-10-17 Dynamically assigning and examining synaptic delay
PCT/US2014/052157 WO2015057305A1 (en) 2013-10-17 2014-08-21 Dynamically assigning and examining synaptic delay

Publications (2)

Publication Number Publication Date
CN105659260A CN105659260A (zh) 2016-06-08
CN105659260B true CN105659260B (zh) 2018-06-29

Family

ID=51492476

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201480056520.2A Active CN105659260B (zh) 2013-10-17 2014-08-21 动态地指派和检查突触延迟

Country Status (7)

Country Link
US (1) US9536190B2 (enExample)
EP (1) EP3058517A1 (enExample)
JP (1) JP6219509B2 (enExample)
KR (1) KR101782760B1 (enExample)
CN (1) CN105659260B (enExample)
CA (1) CA2926034A1 (enExample)
WO (1) WO2015057305A1 (enExample)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10084620B1 (en) 2017-03-01 2018-09-25 Intel Corporation Neural network-based systems for high speed data links
CN108256638B (zh) * 2018-01-05 2021-06-22 上海兆芯集成电路有限公司 微处理器电路以及执行神经网络运算的方法
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
US11461645B2 (en) 2019-12-02 2022-10-04 International Business Machines Corporation Initialization of memory networks
CN111563593B (zh) * 2020-05-08 2023-09-15 北京百度网讯科技有限公司 神经网络模型的训练方法和装置

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5666518A (en) * 1995-06-26 1997-09-09 The United States Of America As Represented By The Secretary Of The Air Force Pattern recognition by simulated neural-like networks
US5877954A (en) 1996-05-03 1999-03-02 Aspen Technology, Inc. Hybrid linear-neural network process control
US8335564B2 (en) 2005-05-27 2012-12-18 Rami Rom Ventricle pacing during atrial fibrillation episodes
US7958071B2 (en) * 2007-04-19 2011-06-07 Hewlett-Packard Development Company, L.P. Computational nodes and computational-node networks that include dynamical-nanodevice connections
US9147156B2 (en) * 2011-09-21 2015-09-29 Qualcomm Technologies Inc. Apparatus and methods for synaptic update in a pulse-coded network
US8725662B2 (en) 2011-09-21 2014-05-13 Brain Corporation Apparatus and method for partial evaluation of synaptic updates based on system events
US9092735B2 (en) 2011-09-21 2015-07-28 Qualcomm Incorporated Method and apparatus for structural delay plasticity in spiking neural networks

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
Extending SpikeProp;Benjamin Schrauwen etal.;《IEEE》;20041231;第471-475页 *

Also Published As

Publication number Publication date
CN105659260A (zh) 2016-06-08
CA2926034A1 (en) 2015-04-23
US9536190B2 (en) 2017-01-03
EP3058517A1 (en) 2016-08-24
JP6219509B2 (ja) 2017-10-25
WO2015057305A1 (en) 2015-04-23
KR20160071437A (ko) 2016-06-21
KR101782760B1 (ko) 2017-09-27
US20150112908A1 (en) 2015-04-23
JP2016537712A (ja) 2016-12-01

Similar Documents

Publication Publication Date Title
CN106030622B (zh) 原位神经网络协同处理
CN105229675B (zh) 尖峰网络的高效硬件实现
US10339041B2 (en) Shared memory architecture for a neural simulator
CN105934766B (zh) 用阴影网络来监视神经网络
CN105580031B (zh) 在多维范围上对包括可分离子系统的系统的评估
CN105874477A (zh) 配置稀疏神经网络
CN106663222A (zh) 神经网络中的分解卷积操作
CN106164939A (zh) 尖峰发放深度置信网络（dbn）中的训练、识别、以及生成
WO2015142503A2 (en) Implementing a neural-network processor
CN105659262A (zh) 在尖峰神经网络中使用重放来实现突触学习
US9959499B2 (en) Methods and apparatus for implementation of group tags for neural models
CN106164940A (zh) 在尖峰神经网络中通过全局标量值来调制可塑性
US9672464B2 (en) Method and apparatus for efficient implementation of common neuron models
US20150278685A1 (en) Probabilistic representation of large sequences using spiking neural network
CN106133763B (zh) 可塑性突触管理
CN105659260B (zh) 动态地指派和检查突触延迟
CN105981054A (zh) 用于将值转换成尖峰的方法
CN105659261A (zh) 尖峰神经元网络中的拥塞避免
US20140365413A1 (en) Efficient implementation of neural population diversity in neural 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