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

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

39 Scopus Citations
View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Article number7460136
Pages (from-to)620-629
Journal / PublicationIEEE Transactions on Neural Networks and Learning Systems
Volume28
Issue number3
Publication statusPublished - 1 Mar 2017

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.

Research Area(s)

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