Skip to main navigation Skip to search Skip to main content

A Two-Time-Scale Neurodynamic Approach to Constrained Minimax Optimization

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

Abstract

This paper presents a two-time-scale neurodynamic approach to constrained minimax optimization using two coupled neural networks. One of the recurrent neural networks is used for minimizing the objective function and another is used for maximization. It is shown that the coupled neurodynamic systems operating in two different time scales work well for minimax optimization. The effectiveness and characteristics of the proposed approach are illustrated using several examples. Furthermore, the proposed approach is applied for H model predictive control.
Original languageEnglish
Pages (from-to)620-629
JournalIEEE Transactions on Neural Networks and Learning Systems
Volume28
Issue number3
Online published27 Apr 2016
DOIs
Publication statusPublished - Mar 2017

Research Keywords

  • Minimax problem
  • neurodynamic optimization
  • recurrent neural networks (RNNs)
  • two-time-scale systems

Fingerprint

Dive into the research topics of 'A Two-Time-Scale Neurodynamic Approach to Constrained Minimax Optimization'. Together they form a unique fingerprint.

Cite this