Improving ANN Generalization Using a Priori Knowledge to Pre-Structure ANNs

Authors

George G. Lendaris, Portland State UniversityFollow
Armin Rest, Portland State University
Thomas R. Misley, Portland State University

Published In

IEEE International Conference on Neural Networks - Conference Proceedings

Document Type

Citation

Publication Date

12-1-1997

Abstract

This is a continuation of work reported by Lendaris at el. (1994) whose objective has been to develop a method that uses certain a priori information about a problem domain to pre-structure artificial neural networks (ANNs) into modules before training. The method is based on a general systems theory methodology, based on information-theoretic ideas, that generates structural information of the problem domain by analyzing I/O pairs from that domain. The notion of performance subset of an ANN structure is described. Extensive experiments on 5-input/1-output and 7-input/1-output Boolean mappings show that significantly improved generalization follows from successful pre-structuring. As the previous work already showed, such pre-structuring also yields improved training speed. © 1997 IEEE.

Rights

Copyright 2007 IEEE

Locate the Document

https://doi.org/10.1109/ICNN.1997.611673

DOI

10.1109/ICNN.1997.611673

Persistent Identifier

https://archives.pdx.edu/ds/psu/37310

Citation Details

Lendaris, G. G., Rest, A., & Misley, T. R. (1997, June). Improving ANN generalization using a priori knowledge to pre-structure ANNs. In Proceedings of International Conference on Neural Networks (ICNN'97) (Vol. 1, pp. 248-253). IEEE.