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

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

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

51 Scopus citations

Abstract

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.

Original languageEnglish
Pages (from-to)901-912
Number of pages12
JournalIEEE Transactions on Neural Networks
Volume9
Issue number5
DOIs
StatePublished - 1 Dec 1998

Keywords

  • Artificial neural network
  • Competitive learning
  • Distributed arithmetic
  • k-winners-take-all
  • Memory-based architecture
  • Systolic array

Fingerprint Dive into the research topics of 'A new k-winners-take-all neural network and its array architecture'. Together they form a unique fingerprint.

Cite this