Using dynamic expansion & contraction approach to generate a feedforward network

D. Young, L. M. Cheng

    Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

    Abstract

    This paper proposes an algorithm to autonomously generate a feedforward network based on the input data. Dynamic expansion & contraction approach (DECA) is used to determine the optimal number of hidden node. The algorithm is applicable to the neural network used for function approximation and pattern classification. The short interval of train/test interleaving will minimize the learning time and avoid over-training the network. That is, a neural network for an application can be generated automatically in optimal time. Together with time-division-multiplexing architecture [1], A hardware reconfigurable ANN architecture with learning capabilities can be realised.
    Original languageEnglish
    Title of host publicationIEEE International Conference on Neural Networks - Conference Proceedings
    PublisherIEEE
    Pages1546-1549
    Volume3
    Publication statusPublished - 1994
    EventProceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7) - Orlando, FL, USA
    Duration: 27 Jun 199429 Jun 1994

    Publication series

    Name
    Volume3

    Conference

    ConferenceProceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7)
    CityOrlando, FL, USA
    Period27/06/9429/06/94

    Fingerprint

    Dive into the research topics of 'Using dynamic expansion & contraction approach to generate a feedforward network'. Together they form a unique fingerprint.

    Cite this