State Sampling Dependence of Hopfield Network Inference
Huang, HP
刊名COMMUNICATIONS IN THEORETICAL PHYSICS
2012
卷号57期号:1页码:169-172
关键词NEURAL NETWORKS FREE-ENERGIES MODEL POPULATION SYSTEM
ISSN号0253-6102
通讯作者Huang, HP (reprint author), Chinese Acad Sci, Inst Theoret Phys, Key Lab Frontiers Theoret Phys, Beijing 100190, Peoples R China.
英文摘要The fully connected Hopfield network is inferred based on observed magnetizations and pairwise correlations. We present the system in the glassy phase with low temperature and high memory load. We find that the inference error is very sensitive to the form of state sampling. When a single state is sampled to compute magnetizations and correlations, the inference error is almost indistinguishable irrespective of the sampled state. However, the error can be greatly reduced if the data is collected with state transitions. Our result holds for different disorder samples and accounts for the previously observed large fluctuations of inference error at low temperatures.
学科主题Physics
收录类别SCI
资助信息National Science Foundation of China [10774150, 10834014]; China 973-Program [2007CB935903, HKUST605010]
语种英语
WOS记录号WOS:000300404700027
公开日期2014-04-25
内容类型期刊论文
源URL[http://ir.itp.ac.cn/handle/311006/15193]  
专题理论物理研究所_理论物理所1978-2010年知识产出
推荐引用方式
GB/T 7714
Huang, HP. State Sampling Dependence of Hopfield Network Inference[J]. COMMUNICATIONS IN THEORETICAL PHYSICS,2012,57(1):169-172.
APA Huang, HP.(2012).State Sampling Dependence of Hopfield Network Inference.COMMUNICATIONS IN THEORETICAL PHYSICS,57(1),169-172.
MLA Huang, HP."State Sampling Dependence of Hopfield Network Inference".COMMUNICATIONS IN THEORETICAL PHYSICS 57.1(2012):169-172.
个性服务
查看访问统计
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。


©版权所有 ©2017 CSpace - Powered by CSpace