ITP OpenIR  > 1978-2010年知识产出
Learning by random walks in the weight space of the Ising perceptron
Huang, Haiping; Zhou, Haijun; Huang, HP , Chinese Acad Sci, Key Lab Frontiers Theoret Phys, Inst Theoret Phys, Beijing 100190, Peoples R China
2010
发表期刊JOURNAL OF STATISTICAL MECHANICS-THEORY AND EXPERIMENT
ISSN1742-5468
期号75页码:-
摘要Several variants of a stochastic local search process for constructing the synaptic weights of an Ising perceptron are studied. In this process, binary patterns are sequentially presented to the Ising perceptron and are then learned as the synaptic weight configuration is modified through a chain of single- or double-weight flips within the compatible weight configuration space of the earlier learned patterns. This process is able to reach a storage capacity of alpha approximate to 0.63 for pattern length N = 101 and alpha approximate to 0.41 for N = 1001. If in addition a relearning process is exploited, the learning performance is further improved to a storage capacity of alpha approximate to 0.80 for N = 101 and alpha approximate to 0.42 for N = 1001. We found that, for a given learning task, the solutions constructed by the random walk learning process are separated by a typical Hamming distance, which decreases with the constraint density a of the learning task; at a fixed value of a, the width of the Hamming distance distribution decreases with N.
部门归属[Huang, HP; Zhou, HJ] Chinese Acad Sci, Key Lab Frontiers Theoret Phys, Inst Theoret Phys, Beijing 100190, Peoples R China; [Zhou, HJ] Chinese Acad Sci, Kavli Inst Theoret Phys China, Inst Theoret Phys, Beijing 100190, Peoples R China
关键词Constraint Satisfaction Problems Neural Network Models Binary Perceptron Storage Capacity Synapses Algorithm Couplings Plasticity Dynamics
学科领域Physics
资助者National Science Foundation of China[10774150, 10834014]; China 973-Program[2007CB935903] ; National Science Foundation of China[10774150, 10834014]; China 973-Program[2007CB935903] ; National Science Foundation of China[10774150, 10834014]; China 973-Program[2007CB935903] ; National Science Foundation of China[10774150, 10834014]; China 973-Program[2007CB935903]
URL查看原文
收录类别SCI
资助者National Science Foundation of China[10774150, 10834014]; China 973-Program[2007CB935903] ; National Science Foundation of China[10774150, 10834014]; China 973-Program[2007CB935903] ; National Science Foundation of China[10774150, 10834014]; China 973-Program[2007CB935903] ; National Science Foundation of China[10774150, 10834014]; China 973-Program[2007CB935903]
WOS记录号WOS:000281744800017
引用统计
被引频次:5[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.itp.ac.cn/handle/311006/5072
专题1978-2010年知识产出
通讯作者Huang, HP , Chinese Acad Sci, Key Lab Frontiers Theoret Phys, Inst Theoret Phys, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714
Huang, Haiping,Zhou, Haijun,Huang, HP , Chinese Acad Sci, Key Lab Frontiers Theoret Phys, Inst Theoret Phys, Beijing 100190, Peoples R China. Learning by random walks in the weight space of the Ising perceptron[J]. JOURNAL OF STATISTICAL MECHANICS-THEORY AND EXPERIMENT,2010(75):-.
APA Huang, Haiping,Zhou, Haijun,&Huang, HP , Chinese Acad Sci, Key Lab Frontiers Theoret Phys, Inst Theoret Phys, Beijing 100190, Peoples R China.(2010).Learning by random walks in the weight space of the Ising perceptron.JOURNAL OF STATISTICAL MECHANICS-THEORY AND EXPERIMENT(75),-.
MLA Huang, Haiping,et al."Learning by random walks in the weight space of the Ising perceptron".JOURNAL OF STATISTICAL MECHANICS-THEORY AND EXPERIMENT .75(2010):-.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Learning by random w(305KB) 开放获取使用许可请求全文
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Huang, Haiping]的文章
[Zhou, Haijun]的文章
[Huang, HP , Chinese Acad Sci, Key Lab Frontiers Theoret Phys, Inst Theoret Phys, Beijing 100190, Peoples R China]的文章
百度学术
百度学术中相似的文章
[Huang, Haiping]的文章
[Zhou, Haijun]的文章
[Huang, HP , Chinese Acad Sci, Key Lab Frontiers Theoret Phys, Inst Theoret Phys, Beijing 100190, Peoples R China]的文章
必应学术
必应学术中相似的文章
[Huang, Haiping]的文章
[Zhou, Haijun]的文章
[Huang, HP , Chinese Acad Sci, Key Lab Frontiers Theoret Phys, Inst Theoret Phys, Beijing 100190, Peoples R China]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。