A gaussian particle swarm optimization for training a feed forward neural network

Haydee Melo, Junzo Watada

    研究成果: Conference contribution

    抄録

    This paper proposes a Gaussian-PSO algorithm which provides the optimized parameters for Feed Forward Neural Network. Recently the Feed Forward Neural Network is widely used in various applications as a result of its advantages such as learning capability, auto-organization and auto-adaptation. However the Neural Network has the disadvantage itself to slowly converge and get easily trapped in a local minima. In this paper, Gaussian distributed random variables are used in the PSO algorithm to enhance its performance and train the weights and bias in the Neural Network. In comparison with the Back Propagation Neural Network, the Gaussian PSO-Neural Network faster converges and is immuned to the local minima.

    本文言語English
    ホスト出版物のタイトルAdvances in Intelligent Systems and Computing
    出版社Springer Verlag
    ページ61-68
    ページ数8
    293
    ISBN(印刷版)9783319074757
    DOI
    出版ステータスPublished - 2014
    イベント12th International Conference on Practical Applications of Agents and Multi-Agent Systems, PAAMS 2014 - Salamanca, Spain
    継続期間: 2014 6 42014 6 6

    出版物シリーズ

    名前Advances in Intelligent Systems and Computing
    293
    ISSN(印刷版)21945357

    Other

    Other12th International Conference on Practical Applications of Agents and Multi-Agent Systems, PAAMS 2014
    国/地域Spain
    CitySalamanca
    Period14/6/414/6/6

    ASJC Scopus subject areas

    • 制御およびシステム工学
    • コンピュータ サイエンス(全般)

    フィンガープリント

    「A gaussian particle swarm optimization for training a feed forward neural network」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

    引用スタイル