On a Constant-Time, Low-Complexity Winner-Take-All Neural Network

Yuen Hsien Tseng, Ja Ling Wu

研究成果: 雜誌貢獻期刊論文同行評審

12 引文 斯高帕斯(Scopus)

摘要

A nearly cost-optimal winner-take-all (WTA) neural network derived from a constant-time sorting network is presented. The resultant WTA network has connection complexity [formula omitted] where s is the depth of cascaded sorting networks. Application of the WTA network to other problems such as nonbinary majority is also included.

原文英語
頁(從 - 到)601-604
頁數4
期刊IEEE Transactions on Computers
44
發行號4
DOIs
出版狀態已發佈 - 1995 四月

ASJC Scopus subject areas

  • 軟體
  • 理論電腦科學
  • 硬體和架構
  • 計算機理論與數學

指紋

深入研究「On a Constant-Time, Low-Complexity Winner-Take-All Neural Network」主題。共同形成了獨特的指紋。

引用此