CN105684002B - 用于使用监督式学习对种类加标签的方法和装置 - Google Patents

用于使用监督式学习对种类加标签的方法和装置 Download PDF

Info

Publication number
CN105684002B
CN105684002B CN201480058854.3A CN201480058854A CN105684002B CN 105684002 B CN105684002 B CN 105684002B CN 201480058854 A CN201480058854 A CN 201480058854A CN 105684002 B CN105684002 B CN 105684002B
Authority
CN
China
Prior art keywords
neuron
network
indexed
neurons
classes
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
CN201480058854.3A
Other languages
English (en)
Chinese (zh)
Other versions
CN105684002A (zh
Inventor
V·古普塔
R·B·托瓦
V·H·陈
R·M·帕特沃德哈
J·莱文
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 CN105684002A publication Critical patent/CN105684002A/zh
Application granted granted Critical
Publication of CN105684002B publication Critical patent/CN105684002B/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
    • 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
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • 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
    • G06N3/09—Supervised learning

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)
  • Testing And Monitoring For Control Systems (AREA)
  • Machine Translation (AREA)
  • Stored Programmes (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
CN201480058854.3A 2013-10-28 2014-10-13 用于使用监督式学习对种类加标签的方法和装置 Active CN105684002B (zh)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US14/065,089 2013-10-28
US14/065,089 US9418331B2 (en) 2013-10-28 2013-10-28 Methods and apparatus for tagging classes using supervised learning
PCT/US2014/060234 WO2015065686A2 (en) 2013-10-28 2014-10-13 Methods and apparatus for tagging classes using supervised learning

Publications (2)

Publication Number Publication Date
CN105684002A CN105684002A (zh) 2016-06-15
CN105684002B true CN105684002B (zh) 2018-07-20

Family

ID=51845519

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201480058854.3A Active CN105684002B (zh) 2013-10-28 2014-10-13 用于使用监督式学习对种类加标签的方法和装置

Country Status (7)

Country Link
US (1) US9418331B2 (OSRAM)
EP (1) EP3063706A2 (OSRAM)
JP (1) JP2016538632A (OSRAM)
KR (1) KR20160076533A (OSRAM)
CN (1) CN105684002B (OSRAM)
CA (1) CA2926334A1 (OSRAM)
WO (1) WO2015065686A2 (OSRAM)

Families Citing this family (31)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9405975B2 (en) 2010-03-26 2016-08-02 Brain Corporation Apparatus and methods for pulse-code invariant object recognition
US9412041B1 (en) 2012-06-29 2016-08-09 Brain Corporation Retinal apparatus and methods
US9275326B2 (en) 2012-11-30 2016-03-01 Brain Corporation Rate stabilization through plasticity in spiking neuron network
US9436909B2 (en) 2013-06-19 2016-09-06 Brain Corporation Increased dynamic range artificial neuron network apparatus and methods
US9552546B1 (en) * 2013-07-30 2017-01-24 Brain Corporation Apparatus and methods for efficacy balancing in a spiking neuron network
US10198691B2 (en) * 2014-06-19 2019-02-05 University Of Florida Research Foundation, Inc. Memristive nanofiber neural networks
EP3158509A4 (en) * 2014-06-19 2018-02-28 University of Florida Research Foundation, Inc. Memristive nanofiber neural networks
US9881349B1 (en) 2014-10-24 2018-01-30 Gopro, Inc. Apparatus and methods for computerized object identification
US10074050B2 (en) * 2015-07-13 2018-09-11 Denso Corporation Memristive neuromorphic circuit and method for training the memristive neuromorphic circuit
CN105243421B (zh) * 2015-10-19 2018-04-03 湖州师范学院 一种基于cnn声发射识别动静态部件间摩擦故障的方法
CN106875004B (zh) * 2017-01-20 2019-09-10 北京灵汐科技有限公司 复合模式神经元信息处理方法和系统
CN110651330A (zh) 2017-05-22 2020-01-03 佛罗里达大学研究基金会 二分忆阻网络中的深度学习
US11348002B2 (en) 2017-10-24 2022-05-31 International Business Machines Corporation Training of artificial neural networks
CN108038543B (zh) * 2017-10-24 2021-01-22 华南师范大学 期望与反期望深度学习方法和神经网络系统
CN107798384B (zh) * 2017-10-31 2020-10-16 山东第一医科大学(山东省医学科学院) 一种基于可进化脉冲神经网络的鸢尾花卉分类方法和装置
US20190042942A1 (en) * 2017-12-07 2019-02-07 Koba Natroshvili Hybrid spiking neural network and support vector machine classifier
US10108903B1 (en) * 2017-12-08 2018-10-23 Cognitive Systems Corp. Motion detection based on machine learning of wireless signal properties
EP3743856A4 (en) * 2018-01-23 2021-10-27 HRL Laboratories, LLC CODING AND LEARNING PROCESS AND SYSTEM DISTRIBUTED IN NEUROMORPHIC NETWORKS ALLOWING RECOGNITION OF PATTERNS
WO2019167884A1 (ja) * 2018-02-28 2019-09-06 富士フイルム株式会社 機械学習方法及び装置、プログラム、学習済みモデル、並びに判別装置
CN112204617B (zh) * 2018-04-09 2023-09-05 杜比实验室特许公司 使用神经网络映射的hdr图像表示
KR102187830B1 (ko) * 2018-06-29 2020-12-07 포항공과대학교 산학협력단 뉴럴 네트워크 하드웨어
WO2020065881A1 (ja) * 2018-09-27 2020-04-02 Tdk株式会社 積和演算器、ニューロモーフィックデバイス及び積和演算方法
KR20200052439A (ko) 2018-10-29 2020-05-15 삼성에스디에스 주식회사 딥러닝 모델의 최적화 시스템 및 방법
WO2020112105A1 (en) * 2018-11-28 2020-06-04 Hewlett-Packard Development Company, L.P. Event-based processing using the output of a deep neural network
JP7279368B2 (ja) * 2019-01-17 2023-05-23 富士通株式会社 学習方法、学習プログラムおよび学習装置
JP7163786B2 (ja) 2019-01-17 2022-11-01 富士通株式会社 学習方法、学習プログラムおよび学習装置
CN110458286B (zh) * 2019-08-14 2022-02-08 中科寒武纪科技股份有限公司 数据处理方法、装置、计算机设备和存储介质
US11684921B1 (en) * 2019-08-16 2023-06-27 Leidos, Inc. Pocket detection pouch
KR102787375B1 (ko) 2019-12-27 2025-03-27 삼성전자주식회사 신경망의 데이터 입력 및 출력을 제어하는 제어 방법 및 장치
CN113408613B (zh) * 2021-06-18 2022-07-19 电子科技大学 一种基于延迟机制的单层图像分类方法
US12205242B2 (en) * 2021-07-01 2025-01-21 Leidos, Inc. Method and system for accelerating rapid class augmentation for object detection in deep neural networks

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2012089360A1 (en) * 2010-12-30 2012-07-05 International Business Machines Corporation Electronic synapses for reinforcement learning
CN103078054A (zh) * 2013-01-04 2013-05-01 华中科技大学 一种模拟生物神经元和神经突触的单元、装置及方法

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8781983B2 (en) * 2009-12-29 2014-07-15 Knowmtech, Llc Framework for the evolution of electronic neural assemblies toward directed goals
US7716150B2 (en) 2006-09-28 2010-05-11 Microsoft Corporation Machine learning system for analyzing and establishing tagging trends based on convergence criteria
EP2053523A1 (en) 2007-10-16 2009-04-29 Sony France S.A. Method and apparatus for updating of prototypes
US8682819B2 (en) 2008-06-19 2014-03-25 Microsoft Corporation Machine-based learning for automatically categorizing data on per-user basis
US8655803B2 (en) 2008-12-17 2014-02-18 Xerox Corporation Method of feature extraction from noisy documents
US8843567B2 (en) 2009-11-30 2014-09-23 International Business Machines Corporation Managing electronic messages
US9129220B2 (en) * 2010-07-07 2015-09-08 Qualcomm Incorporated Methods and systems for digital neural processing with discrete-level synapes and probabilistic STDP
US9753959B2 (en) * 2013-10-16 2017-09-05 University Of Tennessee Research Foundation Method and apparatus for constructing a neuroscience-inspired artificial neural network with visualization of neural pathways

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2012089360A1 (en) * 2010-12-30 2012-07-05 International Business Machines Corporation Electronic synapses for reinforcement learning
CN103078054A (zh) * 2013-01-04 2013-05-01 华中科技大学 一种模拟生物神经元和神经突触的单元、装置及方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
A Supervised STDP Based Training Algorithm with Dynamic Threshold Neurons;T. J. Strain等;《2006 International Joint Conference on Neural Networks》;20060721;第3409页第二节-第3413页第五节，图1-2 *

Also Published As

Publication number Publication date
WO2015065686A2 (en) 2015-05-07
KR20160076533A (ko) 2016-06-30
WO2015065686A3 (en) 2015-06-25
CA2926334A1 (en) 2015-05-07
JP2016538632A (ja) 2016-12-08
US9418331B2 (en) 2016-08-16
US20150120626A1 (en) 2015-04-30
CN105684002A (zh) 2016-06-15
EP3063706A2 (en) 2016-09-07

Similar Documents

Publication Publication Date Title
CN105684002B (zh) 用于使用监督式学习对种类加标签的方法和装置
US10339447B2 (en) Configuring sparse neuronal networks
US9542643B2 (en) Efficient hardware implementation of spiking networks
CN105637541B (zh) 用于神经模拟器的共享存储器架构
CN106164939A (zh) 尖峰发放深度置信网络（dbn）中的训练、识别、以及生成
US20150269482A1 (en) Artificial neural network and perceptron learning using spiking neurons
US20150242745A1 (en) Event-based inference and learning for stochastic spiking bayesian networks
US20150212861A1 (en) Value synchronization across neural processors
KR20170031695A (ko) 신경망들에서의 콘볼루션 동작의 분해
CN107077637A (zh) 神经网络中的差分编码
CN105556543B (zh) 针对神经模型的群组标签的实现方案的方法和装置
CN106133755A (zh) 使用尖峰发放神经网络的图像的不变对象表示
CN106164940A (zh) 在尖峰神经网络中通过全局标量值来调制可塑性
US20150278685A1 (en) Probabilistic representation of large sequences using spiking neural network
CN106104585A (zh) 经由阈下调制的模拟信号重构和识别
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
CN106030619A (zh) 用于坐标变换的相位编码
CN105659260B (zh) 动态地指派和检查突触延迟
CN106104586B (zh) 神经元形态模型开发的上下文实时反馈
US20140365413A1 (en) Efficient implementation of neural population diversity in neural system
CN105612536A (zh) 远程地控制和监视神经模型执行的方法和装置

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