A Two-Timescale Duplex Neurodynamic Approach to Biconvex Optimization.
basic_science · Level V
Where this comes from
- Record sourced from PubMed, PMID 30602424.
- Also identified by DOI 10.1109/TNNLS.2018.2884788.
- No licence information is recorded for this record.
- Because redistribution is not established, this page shows the abstract only. Follow the links below for the full text.
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 L<sub>1</sub> -constrained nonnegative matrix factorization.
Medical subject headings
- Computer Simulation
- Neural Networks, Computer
- Pattern Recognition, Automated