USP Electronic Research Repository

Competition and collaboration in cooperative coevolution of Elman recurrent neural networks for time - series prediction

Chandra, Rohitash (2014) Competition and collaboration in cooperative coevolution of Elman recurrent neural networks for time - series prediction. Neural Networks and Learning Systems, 26 . 0-14. ISSN 2162-237X

[img]
Preview
PDF - Published Version
Download (2400Kb) | Preview

    Abstract

    Collaboration enables weak species to survive in an environment where different species compete for limited resources. Cooperative coevolution (CC) is a nature-inspired optimization method that divides a problem into subcomponents and evolves them while genetically isolating them. Problem decomposition is an important aspect in using CC for neuroevolution. CC employs different problem decomposition methods to decompose the neural network training problem into subcomponents. Different problem decomposition methods have features that are helpful at different stages in the evolutionary process. Adaptation, collaboration, and competition are needed for CC, as multiple subpopulations are used to represent the problem. It is important to add collaboration and competition in CC. This paper presents a competitive CC method for training recurrent neural networks for chaotic time-series prediction. Two different instances of the competitive method are proposed that employs different problem decomposition methods to enforce island-based competition. The results show improvement in the performance of the proposed methods in most cases when compared with standalone CC and other methods from the literature.

    Item Type: Journal Article
    Subjects: Q Science > QA Mathematics > QA76 Computer software
    Divisions: Faculty of Science, Technology and Environment (FSTE) > School of Computing, Information and Mathematical Sciences
    Depositing User: Rohitash Chandra
    Date Deposited: 15 May 2015 11:34
    Last Modified: 05 May 2016 09:37
    URI: http://repository.usp.ac.fj/id/eprint/8032
    UNSPECIFIED

    Actions (login required)

    View Item

    Document Downloads

    More statistics for this item...