Coupling weight elimination with genetic algorithms to reduce network size and preserve generalization

    Authors

    G. Bebis; M. Georgiopoulos;T. Kasparis

    Comments

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

    Abbreviated Journal Title

    Neurocomputing

    Keywords

    neural networks; genetic algorithms; weight elimination; pruning; ARTIFICIAL NEURAL NETWORKS; Computer Science, Artificial Intelligence

    Abstract

    Recent theoretical results support that decreasing the number of free parameters in a neural network (i.e., weights) can improve generalization. These results have triggered the development of many approaches which try to determine an ''appropriate'' network size for a given problem. The main goal has been to find a network size just large enough to capture the general class properties of the data. In some cases, however, network size is not reduced significantly or the reduction is satisfactory but generalization is affected. In this paper, we propose the coupling of genetic algorithms with weight elimination. Our objective is not only to significantly reduce network size, by pruning larger size networks, but also to preserve generalization, that is, to come up with pruned networks which generalize as good or even better than their unpruned counterparts. The innovation of our work relies on a fitness function which uses an adaptive parameter to encourage reproduction of networks having small size and good generalization. The proposed approach has been tested using both artificial and real databases demonstrating good performance.

    Journal Title

    Neurocomputing

    Volume

    17

    Issue/Number

    3-4

    Publication Date

    1-1-1997

    Document Type

    Article

    Language

    English

    First Page

    167

    Last Page

    194

    WOS Identifier

    WOS:A1997YF09602324

    ISSN

    0925-2312

    Share

    COinS