Parallel nonlinear optimization techniques for training neural networks

In this paper, we propose the use of parallel quasi-Newton (QN) optimization techniques to improve the rate of convergence of the training process for neural networks. The parallel algorithms are developed by using the self-scaling quasi-Newton (SSQN) methods. At the beginning of each iteration, a s...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on neural networks Jg. 14; H. 6; S. 1460 - 1468
Hauptverfasser: Phua, P.K.H., Daohua Ming
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States IEEE 01.11.2003
Schlagworte:
Backpropagation algorithms
Benchmark testing
Character generation
Convergence
Feedforward neural networks
Least squares methods
Neural networks
Neurons
Optimization methods
Parallel algorithms
ISSN:1045-9227
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In this paper, we propose the use of parallel quasi-Newton (QN) optimization techniques to improve the rate of convergence of the training process for neural networks. The parallel algorithms are developed by using the self-scaling quasi-Newton (SSQN) methods. At the beginning of each iteration, a set of parallel search directions is generated. Each of these directions is selectively chosen from a representative class of QN methods. Inexact line searches are then carried out to estimate the minimum point along each search direction. The proposed parallel algorithms are tested over a set of nine benchmark problems. Computational results show that the proposed algorithms outperform other existing methods, which are evaluated over the same set of test problems.
Bibliographie:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ObjectType-Article-1
ObjectType-Feature-2
ISSN:1045-9227
DOI:10.1109/TNN.2003.820670