USP Electronic Research Repository

Multi - step - ahead chaotic time series prediction using coevolutionary recurrent neural networks

Hussein, Shamina and Chandra, R. and Sharma, Anuraganand (2016) Multi - step - ahead chaotic time series prediction using coevolutionary recurrent neural networks. [Conference Proceedings]

[img]
Preview
PDF - Draft Version
Download (1051Kb) | Preview

    Abstract

    Multi-step-ahead time series prediction has been one of the greatest challenges for machine learning. Recurrent neural networks (RNN) can efficiently model temporal sequences and have been promising for multi-step time series prediction. Cooperative neuro-evolution has been used for training RNNs with promising performance for single step ahead time series prediction. This paper employs cooperative neuro-evolution of RNNs for multi-step ahead prediction. The RNN recursively predicts the next values in the horizon where the output from the single-step ahead prediction are the input for predicting the next value in the horizon. The performance of cooperative neuro-evolution is compared with back-propagation through time (BPTT) learning algorithm. The results are promising which shows that cooperative neuro-evolution performs better compared to BPTT for most cases.

    Item Type: Conference Proceedings
    Additional Information: DOI: 10.1109/CEC.2016.7744179
    Subjects: T Technology > TJ Mechanical engineering and machinery
    Divisions: Faculty of Science, Technology and Environment (FSTE) > School of Computing, Information and Mathematical Sciences
    Depositing User: Repo Editor
    Date Deposited: 24 Jan 2017 14:10
    Last Modified: 24 Mar 2017 17:17
    URI: http://repository.usp.ac.fj/id/eprint/9390
    UNSPECIFIED

    Actions (login required)

    View Item

    Document Downloads

    More statistics for this item...