Loughborough University
Leicestershire, UK
LE11 3TU
+44 (0)1509 263171
Loughborough University

Loughborough University Institutional Repository

Please use this identifier to cite or link to this item: https://dspace.lboro.ac.uk/2134/37222

Title: A memetic imperialist competitive algorithm with chaotic maps for multi-layer neural network training
Authors: Mousavirad, Seyed Jalaleddin
Bidgoli, Azam Asilian
Ebrahimpour-Komleh, Hossein
Schaefer, Gerald
Keywords: Neural network training
Imperialist competitive algorithm
Memetic computing
Chaotic map
Issue Date: 2019
Publisher: Inderscience
Citation: MOUSAVIRAD, S.J. ... et al., 2019. A memetic imperialist competitive algorithm with chaotic maps for multi-layer neural network training. International Journal of Bio-Inspired Computation, Forthcoming.
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. Experiment results confirm our proposed algorithm to be highly competitive compared to other recently reported methods.
Description: This paper is in closed access until 12 months after publication.
Version: Accepted for publication
URI: https://dspace.lboro.ac.uk/2134/37222
Publisher Link: https://www.inderscience.com/info/ingeneral/forthcoming.php?jcode=ijbic
ISSN: 1758-0366
Appears in Collections:Closed Access (Computer Science)

Files associated with this item:

File Description SizeFormat
ijbic18.pdfAccepted version259.37 kBAdobe PDFView/Open


SFX Query

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.