Function approximation with spiked random networks

    Authors

    E. Gelenbe; Z. H. Mao;Y. D. Li

    Comments

    Authors: contact us about adding a copy of your work at STARS@ucf.edu

    Abbreviated Journal Title

    IEEE Trans. Neural Netw.

    Keywords

    function approximation random neural networks; spiked neural networks; NEURAL NETWORKS; COMPRESSION; Computer Science, Artificial Intelligence; Computer Science, Hardware &; Architecture; Computer Science, Theory & Methods; Engineering, ; Electrical & Electronic

    Abstract

    This paper examines the function approximation properties of the "random neural-network model" or GNN, The output of the GNN can be computed from the firing probabilities of selected neurons. We consider a feedforward Bipolar GNN (BGNN) model which has both "positive and negative neurons" in the output layer, and prove that the BGNN is a universal function approximator, Specifically, for any f is an element of C([0, 1](s)) and any epsilon > 0, we show that there exists a feedforward BGNN which approximates I uniformly with error less than epsilon. We also show that after some appropriate clamping operation on its output, the feedforward GNN is also a universal function approximator.

    Journal Title

    Ieee Transactions on Neural Networks

    Volume

    10

    Issue/Number

    1

    Publication Date

    1-1-1999

    Document Type

    Article

    Language

    English

    First Page

    3

    Last Page

    9

    WOS Identifier

    WOS:000077977800002

    ISSN

    1045-9227

    Share

    COinS