Associative mapping network without redundant local minima

Ja Ling Wu, Yuen Shien Tseng

研究成果: 雜誌貢獻期刊論文同行評審

1 引文 斯高帕斯(Scopus)

摘要

When neural networks are used for associative memory or associative mapping, there always exist in their corresponding energy functions unexpected local minima to which networks may converge. These unexpected local minima, corresponding to spurious outputs or crosstalks, are caused by improperly distributed stored patterns, especially those that are not mutually orthogonal or not linearly independent. An associative mapping network, named the correlation network, is thus proposed to solve this problem. This non-linear network directly accesses its stored patterns and does not require high-order dimension expansion, by introducing the thresholds which carry the correlating information among stored patterns. Furthermore, correlation networks would never have redundant local minima in their energy functions for any pattern stored in the network.

原文英語
頁(從 - 到)899-916
頁數18
期刊International Journal of Electronics
71
發行號6
DOIs
出版狀態已發佈 - 1991 十二月

ASJC Scopus subject areas

  • 電氣與電子工程

指紋

深入研究「Associative mapping network without redundant local minima」主題。共同形成了獨特的指紋。

引用此