Winner-take-all neural network and its application to minimax optimisation problems

A. Cichocki, R. Unbehauen

Research output: Contribution to journalArticlepeer-review

11 Citations (Scopus)

Abstract

A new and simple winner-take-all neural subnetwork suitable for VLSI CMOS implementation is proposed. The subnetwork is used for the real-time solving of minimax optimisation problems. In particular, the Letter shows how to solve, in real time, an over-determined system of linear equations by using the Chebyshev L norm criterion and a neural network approach. The validity and performance of the network have been checked by extensive computer simulation of different minimax optimisation problems.

Original languageEnglish
Pages (from-to)2026-2028
Number of pages3
JournalElectronics Letters
Volume27
Issue number22
DOIs
Publication statusPublished - 24 Oct 1991
Externally publishedYes

Keywords

  • Circuit theory and design
  • Neural networks
  • Optimisation

Fingerprint

Dive into the research topics of 'Winner-take-all neural network and its application to minimax optimisation problems'. Together they form a unique fingerprint.

Cite this