CN103548042B - 用于对初级视皮层简单细胞和其他神经电路的输入突触进行无监督训练的方法和设备 - Google Patents

用于对初级视皮层简单细胞和其他神经电路的输入突触进行无监督训练的方法和设备 Download PDF

Info

Publication number
CN103548042B
CN103548042B CN201280024956.4A CN201280024956A CN103548042B CN 103548042 B CN103548042 B CN 103548042B CN 201280024956 A CN201280024956 A CN 201280024956A CN 103548042 B CN103548042 B CN 103548042B
Authority
CN
China
Prior art keywords
sum
output
circuits
circuit
weight
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
CN201280024956.4A
Other languages
English (en)
Chinese (zh)
Other versions
CN103548042A (zh
Inventor
V·阿帕林
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 CN103548042A publication Critical patent/CN103548042A/zh
Application granted granted Critical
Publication of CN103548042B publication Critical patent/CN103548042B/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
    • G06N3/06—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
    • G06N3/06—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
    • G06N3/065—Analogue means

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Theoretical Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Computational Linguistics (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Neurology (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)
  • Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
  • Heterocyclic Carbon Compounds Containing A Hetero Ring Having Oxygen Or Sulfur (AREA)
CN201280024956.4A 2011-05-25 2012-05-25 用于对初级视皮层简单细胞和其他神经电路的输入突触进行无监督训练的方法和设备 Active CN103548042B (zh)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US13/115,154 US8583577B2 (en) 2011-05-25 2011-05-25 Method and apparatus for unsupervised training of input synapses of primary visual cortex simple cells and other neural circuits
US13/115,154 2011-05-25
PCT/US2012/039704 WO2012162663A1 (en) 2011-05-25 2012-05-25 Method and apparatus for unsupervised training of input synapses of primary visual cortex simple cells and other neural circuits

Publications (2)

Publication Number Publication Date
CN103548042A CN103548042A (zh) 2014-01-29
CN103548042B true CN103548042B (zh) 2016-08-10

Family

ID=46208849

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201280024956.4A Active CN103548042B (zh) 2011-05-25 2012-05-25 用于对初级视皮层简单细胞和其他神经电路的输入突触进行无监督训练的方法和设备

Country Status (6)

Country Link
US (1) US8583577B2 (https=)
EP (1) EP2715620B1 (https=)
JP (2) JP6113719B2 (https=)
KR (1) KR101549767B1 (https=)
CN (1) CN103548042B (https=)
WO (1) WO2012162663A1 (https=)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20210134066A (ko) * 2016-08-03 2021-11-08 가부시키가이샤 한도오따이 에네루기 켄큐쇼 촬상 장치, 촬상 모듈, 전자 기기, 및 촬상 시스템
US11250316B2 (en) 2018-08-10 2022-02-15 International Business Machines Corporation Aggregate adjustments in a cross bar neural network
CN113160027A (zh) * 2020-01-23 2021-07-23 华为技术有限公司 一种图像处理模型训练方法及装置

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH03102563A (ja) * 1989-09-18 1991-04-26 Fujitsu Ltd ニューラルネット
US5329610A (en) * 1992-05-19 1994-07-12 Intel Corporation Neural network employing absolute value calculating synapse
EP0652525A2 (en) * 1993-11-09 1995-05-10 AT&T Corp. High efficiency learning network

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7769513B2 (en) * 2002-09-03 2010-08-03 Automotive Technologies International, Inc. Image processing for vehicular applications applying edge detection technique
US5771312A (en) * 1996-07-01 1998-06-23 Ramot University Authority For Applied Research & Industrial Development Ltd. Method for automatic partial white balance correction
GB9902115D0 (en) * 1999-02-01 1999-03-24 Axeon Limited Neural networks
US6912307B2 (en) * 2001-02-07 2005-06-28 Ramot Fyt Tel Aviv University Ltd. Method for automatic color and intensity contrast adjustment of still and video images
US7711663B2 (en) * 2006-03-27 2010-05-04 Board Of Trustees Of Michigan State University Multi-layer development network having in-place learning
WO2007137047A2 (en) * 2006-05-16 2007-11-29 Greer Douglas S Modeling the neocortex
US9443141B2 (en) * 2008-06-02 2016-09-13 New York University Method, system, and computer-accessible medium for classification of at least one ICTAL state
US9129220B2 (en) * 2010-07-07 2015-09-08 Qualcomm Incorporated Methods and systems for digital neural processing with discrete-level synapes and probabilistic STDP
US9092736B2 (en) * 2010-07-07 2015-07-28 Qualcomm Incorporated Communication and synapse training method and hardware for biologically inspired networks
US8892485B2 (en) * 2010-07-08 2014-11-18 Qualcomm Incorporated Methods and systems for neural processor training by encouragement of correct output
US9129222B2 (en) * 2011-06-22 2015-09-08 Qualcomm Incorporated Method and apparatus for a local competitive learning rule that leads to sparse connectivity

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH03102563A (ja) * 1989-09-18 1991-04-26 Fujitsu Ltd ニューラルネット
US5329610A (en) * 1992-05-19 1994-07-12 Intel Corporation Neural network employing absolute value calculating synapse
EP0652525A2 (en) * 1993-11-09 1995-05-10 AT&T Corp. High efficiency learning network

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
A combinational digital logic approach to STDP;ANDREW CASSIDY等;《CIRCUITS AND SYSTEMS(ISCAS),2011 IEEE》;20110515;第673-676页 *
Edge Detection Model Based on Involuntary Eye Movements of the Eye-Retina System;András Róka等;《Acta Polytechnica Hungarica》;20070101;第31-46页 *

Also Published As

Publication number Publication date
EP2715620B1 (en) 2016-12-14
KR101549767B1 (ko) 2015-09-02
WO2012162663A1 (en) 2012-11-29
US20120303566A1 (en) 2012-11-29
JP2016139420A (ja) 2016-08-04
EP2715620A1 (en) 2014-04-09
JP2014517973A (ja) 2014-07-24
US8583577B2 (en) 2013-11-12
JP6113719B2 (ja) 2017-04-12
JP6117392B2 (ja) 2017-04-19
CN103548042A (zh) 2014-01-29
KR20140027415A (ko) 2014-03-06

Similar Documents

Publication Publication Date Title
Panda et al. Asp: Learning to forget with adaptive synaptic plasticity in spiking neural networks
US8892485B2 (en) Methods and systems for neural processor training by encouragement of correct output
CN110826602B (zh) 基于膜电位调控脉冲神经网络的图像分类方法、系统
US9418331B2 (en) Methods and apparatus for tagging classes using supervised learning
CN103620624B (zh) 用于导致稀疏连通性的局部竞争性学习规则的方法和装置
EP3121767A1 (en) Methods and systems for implementing deep spiking neural networks
KR20170031695A (ko) 신경망들에서의 콘볼루션 동작의 분해
CN109416758A (zh) 神经网络及神经网络训练的方法
US9652711B2 (en) Analog signal reconstruction and recognition via sub-threshold modulation
US20160004961A1 (en) Feature extraction using a neurosynaptic system
CN106133755A (zh) 使用尖峰发放神经网络的图像的不变对象表示
WO2015167765A2 (en) Temporal spike encoding for temporal learning
CN110826437A (zh) 基于生物神经网络的智能机器人控制方法、系统、装置
US9361545B2 (en) Methods and apparatus for estimating angular movement with a single two dimensional device
Ibrayev et al. A design of HTM spatial pooler for face recognition using memristor-CMOS hybrid circuits
WO2015148254A2 (en) Invariant object representation of images using spiking neural networks
CN103548042B (zh) 用于对初级视皮层简单细胞和其他神经电路的输入突触进行无监督训练的方法和设备
Schuman et al. Variable structure dynamic artificial neural networks
Li et al. Pattern recognition of spiking neural networks based on visual mechanism and supervised synaptic learning
CA2898216C (en) Methods and systems for implementing deep spiking neural networks
US8843426B2 (en) Method and apparatus of primary visual cortex simple cell training and operation
Vaila et al. Spiking CNNs with PYNN and NEURON
Meyer et al. Verilog-A model of ferroelectric memristors dedicated to neuromorphic design

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant