A Two-Timescale Duplex Neurodynamic Approach to Biconvex Optimization.
IEEE Trans Neural Netw Learn Syst
; 30(8): 2503-2514, 2019 08.
Article
em En
| MEDLINE
| ID: mdl-30602424
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.
Texto completo:
1
Coleções:
01-internacional
Base de dados:
MEDLINE
Assunto principal:
Simulação por Computador
/
Reconhecimento Automatizado de Padrão
/
Redes Neurais de Computação
Tipo de estudo:
Prognostic_studies
Limite:
Humans
Idioma:
En
Revista:
IEEE Trans Neural Netw Learn Syst
Ano de publicação:
2019
Tipo de documento:
Article