A new k-winners-take-all neural network and its array architecture

Jui Cheng Yen*, Jiun-In  Guo, Hun Chen Chen

*此作品的通信作者

研究成果: Article同行評審

53 引文 斯高帕斯(Scopus)

摘要

In this paper, a new neural-network model called WINSTRON and its novel array architecture are proposed. Based on a competitive learning algorithm that is originated from the coarse-fine competition, WINSTRON can identify the k larger elements or the k smaller ones in a data set. We will then prove that WINSTRON converges to the correct state in any situation. In addition, the convergence rates of WINSTRON for three special data distributions will be derived. In order to realize WINSTRON, its array architecture with low hardware complexity and high computing speed is also detailed. Finally, simulation results are included to demonstrate its effectiveness and its advantages over three existing networks.

原文English
頁(從 - 到)901-912
頁數12
期刊IEEE Transactions on Neural Networks
9
發行號5
DOIs
出版狀態Published - 1998

指紋

深入研究「A new k-winners-take-all neural network and its array architecture」主題。共同形成了獨特的指紋。

引用此