Competitive learning with subspace search in transform domain

Wen Jyi Hwang*, Shi Chiang Liao

*此作品的通信作者

研究成果: 雜誌貢獻期刊論文同行評審

摘要

A new competitive learning (CL) algorithm with k-winners-take-all activation is presented. The k winning neurons for updating are those best matching the input vector in the wavelet domain with subspace search. Simulation results show that the algorithm gives a better performance than that of the traditional CL algorithm while requiring much less computational time.

原文英語
頁(從 - 到)1240-1241
頁數2
期刊Electronics Letters
34
發行號12
DOIs
出版狀態已發佈 - 1998 六月 11
對外發佈

ASJC Scopus subject areas

  • 電氣與電子工程

指紋

深入研究「Competitive learning with subspace search in transform domain」主題。共同形成了獨特的指紋。

引用此