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

24 October 1991

journal article
Published by Institution of Engineering and Technology (IET) in Electronics Letters

Vol. 27 (22) , 2026-2028
https://doi.org/10.1049/el:19911255

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.

Keywords

This publication has 3 references indexed in Scilit:

Neural networks in minimax programming
Published by Institute of Electrical and Electronics Engineers (IEEE) ,2002
MOS Switched-Capacitor and Continuous-Time Integrated Circuits and Systems
Published by Springer Nature ,1989
Winner-Take-All Networks of O(N) Complexity
Published by Defense Technical Information Center (DTIC) ,1988