Analysis of orthogonal memory patterns
Li YJ; Wang XD; Chen C; Li YJ Acad Sinica Inst Semicond Artificial Neural Network Grp POB 912 Beijing 100083 Peoples R China.
1998
会议名称5th International Conference on Neural Information Processing (ICONIP 98) / 1998 Annual Conference of the Japanese-Neural-Network-Society (JNNS 98)
会议录名称ICONIP'98: THE FIFTH INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING JOINTLY WITH JNNS'98: THE 1998 ANNUAL CONFERENCE OF THE JAPANESE NEURAL NETWORK SOCIETY - PROCEEDINGS, VOLS 1-3
页码939-942
会议日期OCT 21-23, 1998
会议地点KITAKYUSHU, JAPAN
出版地1-3 KANDA NISHIKI-CHO, CHIYODA-KU, TOKYO, 101, JAPAN
出版者OHMSHA LTD
ISBN4-274-90259-5
部门归属acad sinica, inst semicond, artificial neural network grp, beijing 100083, peoples r china
摘要It is well known that the storage capacity may be large if all memory patterns are orthogonal to each other. In this paper, a clear description is given about the relation between the dimension N and the maximal number of orthogonal vectors with components +/-1, and also the conception of attractive index is proposed to estimate the basin of attraction. Theoretic analysis and computer simulation show that each memory pattern's basin of attraction contains at least one Hamming ball when the storage capacity is less than 0.33N which is better than usual 0.15 N.
关键词Orthogonal Memory Patterns Dimension Storage Capacity Basin Of Attraction Hamming Ball Neural Networks
学科领域人工智能
主办者Japanese Neural Network Soc.; Asian Pacific Neural Network Assembly.
收录类别CPCI-S
语种英语
文献类型会议论文
条目标识符http://ir.semi.ac.cn/handle/172111/13809
专题中国科学院半导体研究所(2009年前)
通讯作者Li YJ Acad Sinica Inst Semicond Artificial Neural Network Grp POB 912 Beijing 100083 Peoples R China.
推荐引用方式
GB/T 7714
Li YJ,Wang XD,Chen C,et al. Analysis of orthogonal memory patterns[C]. 1-3 KANDA NISHIKI-CHO, CHIYODA-KU, TOKYO, 101, JAPAN:OHMSHA LTD,1998:939-942.
条目包含的文件
条目无相关文件。
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
[Li YJ]的文章
[Wang XD]的文章
[Chen C]的文章
百度学术
百度学术中相似的文章
[Li YJ]的文章
[Wang XD]的文章
[Chen C]的文章
必应学术
必应学术中相似的文章
[Li YJ]的文章
[Wang XD]的文章
[Chen C]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。