A Two-Timescale Duplex Neurodynamic Approach to Biconvex Optimization

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

72 Scopus Citations
View graph of relations


Original languageEnglish
Article number8594585
Pages (from-to)2503-2514
Journal / PublicationIEEE Transactions on Neural Networks and Learning Systems
Issue number8
Online published28 Dec 2018
Publication statusPublished - Aug 2019


This paper presents a two-timescale duplex neurodynamic system for constrained biconvex optimization. The two-timescale duplex neurodynamic system consists of two recurrent neural networks (RNNs) operating collaboratively at two timescales. By operating on two timescales, RNNs are able to avoid instability. In addition, based on the convergent states of the two RNNs, particle swarm optimization is used to optimize initial states of the RNNs to avoid local minima. It is proven that the proposed system is globally convergent to the global optimum with probability one. The performance of the two-timescale duplex neurodynamic system is substantiated based on the benchmark problems. Furthermore, the proposed system is applied for L1-constrained nonnegative matrix factorization.

Research Area(s)

  • Biconvex optimization, duplex neurodynamic system, two-timescale system