CN105556543B - 针对神经模型的群组标签的实现方案的方法和装置 - Google Patents

针对神经模型的群组标签的实现方案的方法和装置 Download PDF

Info

Publication number
CN105556543B
CN105556543B CN201480051708.8A CN201480051708A CN105556543B CN 105556543 B CN105556543 B CN 105556543B CN 201480051708 A CN201480051708 A CN 201480051708A CN 105556543 B CN105556543 B CN 105556543B
Authority
CN
China
Prior art keywords
group
parameters
synapses
artificial neurons
artificial
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
CN201480051708.8A
Other languages
English (en)
Chinese (zh)
Other versions
CN105556543A (zh
Inventor
D·J·朱利安
J·A·莱温
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 CN105556543A publication Critical patent/CN105556543A/zh
Application granted granted Critical
Publication of CN105556543B publication Critical patent/CN105556543B/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
    • G06N3/045—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
    • G06N3/082—Learning methods modifying the architecture, e.g. adding, deleting or silencing nodes or connections

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Molecular Biology (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Image Analysis (AREA)
  • Nitrogen Condensed Heterocyclic Rings (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Feedback Control In General (AREA)
CN201480051708.8A 2013-09-25 2014-08-18 针对神经模型的群组标签的实现方案的方法和装置 Active CN105556543B (zh)

Applications Claiming Priority (5)

Application Number Priority Date Filing Date Title
US201361882465P 2013-09-25 2013-09-25
US61/882,465 2013-09-25
US14/268,152 2014-05-02
US14/268,152 US9959499B2 (en) 2013-09-25 2014-05-02 Methods and apparatus for implementation of group tags for neural models
PCT/US2014/051469 WO2015047589A2 (en) 2013-09-25 2014-08-18 Methods and apparatus for implementation of group tags for neural models

Publications (2)

Publication Number Publication Date
CN105556543A CN105556543A (zh) 2016-05-04
CN105556543B true CN105556543B (zh) 2018-11-23

Family

ID=52691891

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201480051708.8A Active CN105556543B (zh) 2013-09-25 2014-08-18 针对神经模型的群组标签的实现方案的方法和装置

Country Status (9)

Country Link
US (1) US9959499B2 (enExample)
EP (1) EP3050004A2 (enExample)
JP (1) JP2016536657A (enExample)
KR (1) KR20160058825A (enExample)
CN (1) CN105556543B (enExample)
BR (1) BR112016006482A2 (enExample)
CA (1) CA2921831A1 (enExample)
TW (1) TW201523463A (enExample)
WO (1) WO2015047589A2 (enExample)

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2017068490A1 (en) * 2015-10-23 2017-04-27 Semiconductor Energy Laboratory Co., Ltd. Semiconductor device and electronic device
CN108255775A (zh) * 2016-12-28 2018-07-06 上海磁宇信息科技有限公司 用于细胞阵列计算系统的细胞阵列总线广播方法
US20190102669A1 (en) * 2017-09-29 2019-04-04 Intel Corporation Global and local time-step determination schemes for neural networks
US11195079B2 (en) * 2017-11-22 2021-12-07 Intel Corporation Reconfigurable neuro-synaptic cores for spiking neural network
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
KR102756358B1 (ko) 2018-12-18 2025-01-17 삼성전자주식회사 검출기, 객체 검출 방법, 학습기 및 도메인 변환을 위한 학습 방법
US11625583B2 (en) * 2019-02-13 2023-04-11 Mipsology SAS Quality monitoring and hidden quantization in artificial neural network computations
EP4035127A4 (en) 2019-09-24 2023-10-18 Applied Materials, Inc. INTERACTIVE TRAINING OF A MACHINE LEARNING MODEL FOR TISSUE SEGMENTATION
CN113065647B (zh) * 2021-03-30 2023-04-25 西安电子科技大学 加速神经网络的计算-存储通信系统及通信方法
CN115169547B (zh) * 2022-09-09 2022-11-29 深圳时识科技有限公司 神经形态芯片及电子设备

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5276769A (en) * 1989-03-13 1994-01-04 Sharp Kabushiki Kaisha Neural network learning apparatus and method
CN102959566A (zh) * 2010-07-07 2013-03-06 高通股份有限公司 用于具有离散级突触和概率性stdp的数字神经处理的方法和系统

Family Cites Families (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3172163B2 (ja) * 1990-05-07 2001-06-04 富士通株式会社 ニューラルネットワークにおける結合のグループ単位学習調整方式
JPH06348675A (ja) * 1993-06-07 1994-12-22 Ebara Corp ニューロコンピュータ応用機器およびこれを含む機械装置
AU7324396A (en) * 1996-11-05 1998-05-29 Millennium Interactive Limited Process control
JP2002251601A (ja) * 2001-02-22 2002-09-06 Fuji Xerox Co Ltd ニューラルネットワーク処理装置
US8630966B2 (en) 2009-01-27 2014-01-14 Salk Institute For Biological Studies Temporally dynamic artificial neural networks
US8504499B2 (en) 2009-07-15 2013-08-06 The Intellisis Corporation Constant memory implementation of a phase-model neural network
US20110055131A1 (en) * 2009-08-28 2011-03-03 Hung-Han Chen Method of universal computing device
US8738554B2 (en) 2011-09-16 2014-05-27 International Business Machines Corporation Event-driven universal neural network circuit
US8943008B2 (en) * 2011-09-21 2015-01-27 Brain Corporation Apparatus and methods for reinforcement learning in artificial neural networks
US8712939B2 (en) 2011-09-21 2014-04-29 Brain Corporation Tag-based apparatus and methods for neural networks
US9098811B2 (en) * 2012-06-04 2015-08-04 Brain Corporation Spiking neuron network apparatus and methods
US9129221B2 (en) 2012-05-07 2015-09-08 Brain Corporation Spiking neural network feedback apparatus and methods
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
US5276769A (en) * 1989-03-13 1994-01-04 Sharp Kabushiki Kaisha Neural network learning apparatus and method
CN102959566A (zh) * 2010-07-07 2013-03-06 高通股份有限公司 用于具有离散级突触和概率性stdp的数字神经处理的方法和系统

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
"From Swimming to Walking with a Salamander Robot Driven by a Spinal Cord Model";Auke Jan Ijspeert etal.;《SCIENCE》;20070309;第1416-1419页 *
"NeuroML: A Language for Describing Data Driven Models of Neurons and Networks with a High Degree of Biological Detail";Padraig Gleeson etal.;《PLoS Computational Biology》;20100630;第1-19页 *
Padraig Gleeson etal.."NeuroML: A Language for Describing Data Driven Models of Neurons and Networks with a High Degree of Biological Detail".《PLoS Computational Biology》.2010, *

Also Published As

Publication number Publication date
CA2921831A1 (en) 2015-04-02
US9959499B2 (en) 2018-05-01
US20150088796A1 (en) 2015-03-26
BR112016006482A2 (pt) 2017-08-01
CN105556543A (zh) 2016-05-04
KR20160058825A (ko) 2016-05-25
EP3050004A2 (en) 2016-08-03
WO2015047589A3 (en) 2015-05-21
JP2016536657A (ja) 2016-11-24
TW201523463A (zh) 2015-06-16
WO2015047589A2 (en) 2015-04-02

Similar Documents

Publication Publication Date Title
CN105556543B (zh) 针对神经模型的群组标签的实现方案的方法和装置
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
US20150212861A1 (en) Value synchronization across neural processors
WO2015020802A2 (en) Computed synapses for neuromorphic systems
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
WO2015167765A2 (en) Temporal spike encoding for temporal learning
CN105518721B (zh) 用于在人工神经系统中实现断点确定单元的方法和装置
CN106068519A (zh) 用于共用神经元模型的高效实现的方法和装置
US20150213356A1 (en) Method for converting values into spikes
CN106133763B (zh) 可塑性突触管理
EP3058518A2 (en) Congestion avoidance in networks of spiking neurons
CN105659260B (zh) 动态地指派和检查突触延迟
WO2015088689A1 (en) Effecting modulation by global scalar values in a spiking neural network
US9342782B2 (en) Stochastic delay plasticity
US9418332B2 (en) Post ghost plasticity
WO2014197175A2 (en) Efficient implementation of neural population diversity in neural system
US20150278684A1 (en) Time synchronization of spiking neuron models on multiple nodes

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