A memetic imperialist competitive algorithm with chaotic maps for multi-layer neural network training. (27th November 2019)

• Record Type: Journal Article
• Authors: Mousavirad, Seyed Jalaleddin; Bidgoli, Azam Asilian; Komleh, Hossein Ebrahimpour; Schaefer, Gerald
• Is Part Of: International journal of bio-inspired computation. Volume 14:Number 4(2019)
• Page Start: 227
• Page End: 236
• Publication Date: 2019-11-27
• Subjects: neural network training -- imperialist competitive algorithm -- memetic computing -- chaotic map -- back-propagation -- bio-inspired computation; Biologically-inspired computing -- Periodicals; Computational biology -- Periodicals; 572.0285
• Languages: English
• ISSNs: 1758-0366

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.