Title: A memetic imperialist competitive algorithm with chaotic maps for multi-layer neural network training
Authors: Seyed Jalaleddin Mousavirad; Azam Asilian Bidgoli; Hossein Ebrahimpour Komleh; Gerald Schaefer
Addresses: Department of Computer and Electrical Engineering, University of Kashan, Kashan, Iran ' Department of Computer and Electrical Engineering, University of Kashan, Kashan, Iran ' Department of Computer and Electrical Engineering, University of Kashan, Kashan, Iran ' Department of Computer Science, Loughborough University, Loughborough, UK
Abstract: The performance of artificial neural networks (ANNs) is largely dependent on the success of the training process. Gradient descent-based methods are the most widely used training algorithms but have drawbacks such as ending up in local minima. One approach to overcome this is to use population-based algorithms such as the imperialist competitive algorithm (ICA) which is inspired by the imperialist competition between countries. In this paper, we present a new memetic approach for neural network training to improve the efficacy of ANNs. Our proposed approach - memetic imperialist competitive algorithm with chaotic maps (MICA-CM) - is based on a memetic ICA and chaotic maps, which are responsible for exploration of the search space, while back-propagation is used for an effective local search on the best solution obtained by ICA. Experimental results confirm our proposed algorithm to be highly competitive compared to other recently reported methods.
Keywords: neural network training; imperialist competitive algorithm; memetic computing; chaotic map; back-propagation; bio-inspired computation.
International Journal of Bio-Inspired Computation, 2019 Vol.14 No.4, pp.227 - 236
Accepted: 08 Dec 2018
Published online: 27 Nov 2019 *