Abstract
For a given set of reference patterns, many neural network algorithms construct the interconnection weight matrix (IWM) by emphasizing the association of elements within each reference pattern (i.e., intrapattern association), while paying little attention to the association among patterns (i.e., interpattern association). The special features of the reference patterns play an important role in pattern recognition.
© 1989 Optical Society of America
PDF ArticleMore Like This
Wenlu Wang, Shutian Liu, Jie Wu, and Chunfei Li
CMH6 Conference on Lasers and Electro-Optics (CLEO:S&I) 1992
Xiang Y. Yang, Taiwei Lu, and Francis T. S. Yu
MN6 OSA Annual Meeting (FIO) 1990
Taiwei Lu, Sudong Wu, Xin Xu, and Francis T. S. Yu
PD4 Optical Computing (IP) 1989