Modular and hierarchical approach to supervised learning by artificial neural networks leads to neural networks more structured than neural networks in which all neurons fully interconnected. These networks utilize general feedforward flow of information and sparse recurrent connections to achieve dynamical effects. The modular organization, sparsity of modular units and connections, and fact that learning is much more circumscribed are all attractive features for designing neural-network hardware. Learning streamlined by imitating some aspects of biological neural networks.


    Access

    Access via TIB

    Check availability in my library


    Export, share and cite



    Title :

    Modular, Hierarchical Learning By Artificial Neural Networks


    Contributors:

    Published in:

    Publication date :

    1996-03-01



    Type of media :

    Miscellaneous


    Type of material :

    No indication


    Language :

    English





    Forecasting Train Arrival Time Using Modular Artificial Neural Networks

    Cho, H. / Rilett, L. R. / American Society of Civil Engineers | British Library Conference Proceedings | 2002



    Modular Artificial Neural Networks for Solving the Inverse Transportation Planning Problem

    Sadek, Adel W. / Mark, Charles | Transportation Research Record | 2003


    Artificial Neural Networks

    Jategaonkar, Ravindra V. | AIAA | 2015