World-centered representation for neural networks

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

A basic problem for pattern recognition is invariance. This article argues that the traditional full-parallel computation of neural networks that has excluded many useful series computation methods seems improper for the invariance. We introduce a series search mechanism into neural computing. The world-centered recognition is acquired by a pattern-centered memory plus a space search.

源语言英语
主期刊名1997 IEEE International Conference on Neural Networks, ICNN 1997
597-601A
DOI
出版状态已出版 - 1997
活动1997 IEEE International Conference on Neural Networks, ICNN 1997 - Houston, TX, 美国
期限: 9 6月 199712 6月 1997

出版系列

姓名IEEE International Conference on Neural Networks - Conference Proceedings
1
ISSN(印刷版)1098-7576

会议

会议1997 IEEE International Conference on Neural Networks, ICNN 1997
国家/地区美国
Houston, TX
时期9/06/9712/06/97

指纹

探究 'World-centered representation for neural networks' 的科研主题。它们共同构成独一无二的指纹。

引用此