A tabu search algorithm for the training of neural networks
No Thumbnail Available
Date
2009
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
PALGRAVE MACMILLAN LTD
Access Rights
info:eu-repo/semantics/closedAccess
Abstract
The most widely used training algorithm of neural networks (NNs) is back propagation ( BP), a gradient-based technique that requires significant computational effort. Metaheuristic search techniques such as genetic algorithms, tabu search (TS) and simulated annealing have been recently used to cope with major shortcomings of BP such as the tendency to converge to a local optimal and a slow convergence rate. In this paper, an efficient TS algorithm employing different strategies to provide a balance between intensification and diversification is proposed for the training of NNs. The proposed algorithm is compared with other metaheuristic techniques found in literature using published test problems, and found to outperform them in the majority of the test cases.
Description
Keywords
neural networks, supervised training, heuristics, tabu search, simulated annealing, genetic algorithms
Journal or Series
JOURNAL OF THE OPERATIONAL RESEARCH SOCIETY
WoS Q Value
Q2
Scopus Q Value
Q1
Volume
60
Issue
2
