The performances of seven neural network models for traffic control problems in multistage interconnection networks are compared. The decay term, three neuron models, and two heuristics were evaluated. The goal of the traffic control problems is to find conflict-free switching configurations with the maximum throughput. The simulation results show that the hysteresis McCullock-Pitts neuron model without the decay term and with two heuristics has the best performance.


    Access

    Access via TIB

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Comparisons of seven neural network models on traffic control problems in multistage interconnection networks


    Additional title:

    Vergleich von 7 neuronalen Netzmodellen bei Verkehrslenkungsproblemen in mehrstufigen Verbindungsnetzwerken


    Contributors:
    Funabiki, N. (author) / Takefuji, Y. (author) / Lee, K.C. (author)

    Published in:

    Publication date :

    1993


    Size :

    5 Seiten, 18 Quellen




    Type of media :

    Article (Journal)


    Type of material :

    Print


    Language :

    English




    Routing in Optical Multistage Interconnection Networks: A Neural Network Solution

    Giles, C. L. / Goudreau, M. W. | British Library Online Contents | 1995


    Modular architectures for optoelectronic multistage interconnection networks

    Kiamilev, F. / Stevens, E. / Krishnamoorthy, A. V. et al. | British Library Online Contents | 1994


    Polarization-Dependent Gain in SOA-Based Optical Multistage Interconnection Networks

    Liboiron-Ladouceur, O. / Bergman, K. / Boroditsky, M. et al. | British Library Online Contents | 2006



    Implementation of the Parallel Optical Interconnection Network in Multistage Processor Arrays System

    IEEE; Lasers and Electro-Optics Society | British Library Conference Proceedings | 1993