USP Electronic Research Repository

Competitive two - island cooperative coevolution for training Elman recurrent networks for time series prediction

Chandra, Rohitash (2014) Competitive two - island cooperative coevolution for training Elman recurrent networks for time series prediction. [Conference Proceedings] (Unpublished)

[img] PDF - Accepted Version
Download (180Kb)

    Abstract

    Problem decomposition is an important aspect in using cooperative coevolution for neuro-evolution. Cooperative coevolution 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 characteristics that are needed for cooperative coevolution as multiple sub-populations are used to represent the problem. It is important to add collaboration and competition in cooperative coevolution. This paper presents a competitive two-island cooperative coevolution method for training recurrent neural networks on chaotic time series problems. Neural level and Synapse level problem decomposition is used in each of the islands. The results show improvement in performance when compared to standalone cooperative coevolution and other methods from literature.

    Item Type: Conference Proceedings
    Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
    Divisions: Faculty of Science, Technology and Environment (FSTE) > School of Computing, Information and Mathematical Sciences
    Depositing User: Rohitash Chandra
    Date Deposited: 26 May 2014 10:20
    Last Modified: 19 Sep 2016 15:39
    URI: http://repository.usp.ac.fj/id/eprint/7342
    UNSPECIFIED

    Actions (login required)

    View Item

    Document Downloads

    More statistics for this item...