New challenges in US Navy tactical vehicle applications require flexible adaptive structures for real-time intelligent system identification and control tasks. Due to its speed of computation and linear learning behavior, the architecture of lattice-based associative memory networks is particularly attractive. The main problem of these networks is the curse of dimensionality, which means that the memory requirement is exponentially dependent on the input dimension. In this paper, a novel structure called multi-resolution associative memory (MAM) network is proposed to overcome the curse of dimensionality. Preliminary simulations and real-time experiments are performed using this structure, and the results are discussed. A fuzzy rule-bare system is also proposed as a method to implement the heuristic that is at the heart of the MAM network's training algorithm.


    Access

    Access via TIB

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Intelligent training of a multi-resolution associative memory network


    Contributors:
    Menozzi, A. (author) / Mo-Yuen (author) / Cho, C.P. (author)


    Publication date :

    1998


    Size :

    6 Seiten, 11 Quellen




    Type of media :

    Conference paper


    Type of material :

    Print


    Language :

    English




    Associative Memory Network Construction Algorithms

    Brown, N. / Harris, C. J. / Bridgett, N. A. et al. | British Library Conference Proceedings | 1994



    Efficient serial associative memory

    Wilkes, D. / Tsotsos, J.K. | IEEE | 1993


    Dynamical quality in bidirectional associative memory neural network model

    Xiuling, L. | British Library Online Contents | 2013


    A compact optical associative memory

    Burns, T.J. / Rogers, S.K. / Kabrisky, M. et al. | Tema Archive | 1991