Quickly trained artificial neural network with single hidden layer Gaussian units

Goutam Chakraborty*, Norio Shiratori, Shoichi Noguchi

*この研究の対応する著者

    研究成果: Conference contribution

    抄録

    Nonlinear radial basis functions at the single layer hidden units are effective in generating complex nonlinear mapping and at the same time facilitate fast linear learning. In this work, we propose a model and an algorithm to arrive at a near optimum initial configuration very quickly. Thus the position of the hidden units in the input space and the connection weights from the hidden units to the output units, instead of arbitrarily, are optimally set. Simulations on this initial configuration are performed. Different parameters are further trained and their effects experimented.

    本文言語English
    ホスト出版物のタイトル1993 IEEE International Conference on Neural Networks
    編集者 Anon
    Place of PublicationPiscataway, NJ, United States
    出版社Publ by IEEE
    ページ466-472
    ページ数7
    ISBN(印刷版)0780312007
    出版ステータスPublished - 1993
    イベント1993 IEEE International Conference on Neural Networks - San Francisco, CA, USA
    継続期間: 1993 3 281993 4 1

    Other

    Other1993 IEEE International Conference on Neural Networks
    CitySan Francisco, CA, USA
    Period93/3/2893/4/1

    ASJC Scopus subject areas

    • 工学(全般)

    フィンガープリント

    「Quickly trained artificial neural network with single hidden layer Gaussian units」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