Incorporating a priori knowledge into initialized weights for neural classifier

Zhe Chen, T.J. Feng, Tian-Jin Feng, Z. Houkes

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    7 Citations (Scopus)
    64 Downloads (Pure)

    Abstract

    Artificial neural networks (ANN), especially, multilayer perceptrons (MLP) have been widely used in pattern recognition and classification. Nevertheless, how to incorporate a priori knowledge in the design of ANNs is still an open problem. The paper tries to give some insight on this topic emphasizing weight initialization from three perspectives. Theoretical analyses and simulations are offered for validation
    Original languageUndefined
    Title of host publicationProceedings of the IEEE-INNS-ENNS Int.Joint Conference on Neural Networks, Vol II
    Place of PublicationComo, Italy
    PublisherIEEE
    Pages291-296
    ISBN (Print)0-7695-0619-4
    DOIs
    Publication statusPublished - 24 Jul 2000
    Event2000 IEEE-INNS-ENNS International Joint Conference on Neural Networks, IJCNN 2000: Neural Computing: New Challenges and Perspectives for the New Millennium - Como, Italy
    Duration: 24 Jul 200027 Jul 2000

    Publication series

    Name
    PublisherIEEE Press
    Volume2

    Conference

    Conference2000 IEEE-INNS-ENNS International Joint Conference on Neural Networks, IJCNN 2000
    Abbreviated titleIJCNN
    CountryItaly
    CityComo
    Period24/07/0027/07/00

    Keywords

    • IR-16331
    • METIS-113216

    Cite this

    Chen, Z., Feng, T. J., Feng, T-J., & Houkes, Z. (2000). Incorporating a priori knowledge into initialized weights for neural classifier. In Proceedings of the IEEE-INNS-ENNS Int.Joint Conference on Neural Networks, Vol II (pp. 291-296). Como, Italy: IEEE. https://doi.org/10.1109/IJCNN.2000.857911