A Two-Timescale Duplex Neurodynamic Approach to Biconvex Optimization
Research output: Journal Publications and Reviews (RGC: 21, 22, 62) › 21_Publication in refereed journal › peer-review
Author(s)
Related Research Unit(s)
Detail(s)
| Original language | English |
|---|---|
| Article number | 8594585 |
| Pages (from-to) | 2503-2514 |
| Journal / Publication | IEEE Transactions on Neural Networks and Learning Systems |
| Volume | 30 |
| Issue number | 8 |
| Online published | 28 Dec 2018 |
| Publication status | Published - Aug 2019 |
Link(s)
Abstract
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
Citation Format(s)
A Two-Timescale Duplex Neurodynamic Approach to Biconvex Optimization. / Che, Hangjun; Wang, Jun.
In: IEEE Transactions on Neural Networks and Learning Systems, Vol. 30, No. 8, 8594585, 08.2019, p. 2503-2514.Research output: Journal Publications and Reviews (RGC: 21, 22, 62) › 21_Publication in refereed journal › peer-review
