Learning in certainty-factor-based multilayer neural networks for classification

1 January 1998

journal article
Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks

Vol. 9 (1) , 151-158
https://doi.org/10.1109/72.655036

Abstract

The computational framework of rule-based neural networks inherits from the neural network and the inference engine of an expert system. In one approach, the network activation function is based on the certainty factor (CF) model of MYCIN-like systems. In this paper, it is shown theoretically that the neural network using the CF-based activation function requires relatively small sample sizes for correct generalization. This result is also confirmed by empirical studies in several independent domains.

Keywords

This publication has 10 references indexed in Scilit:

The effects of quantization on multilayer neural networks
IEEE Transactions on Neural Networks, 1995
Progress in supervised neural networks
IEEE Signal Processing Magazine, 1993
Knowledge-based connectionism for revising domain theories
IEEE Transactions on Systems, Man, and Cybernetics, 1993
Combining Connectionist and Symbolic Learning to Refine Certainty Factor Rule Bases
Connection Science, 1993
Back-propagation learning in expert networks
IEEE Transactions on Neural Networks, 1992
Learnability and the Vapnik-Chervonenkis dimension
Journal of the ACM, 1989
What Size Net Gives Valid Generalization?
Neural Computation, 1989
A theory of the learnable
Communications of the ACM, 1984
Some special vapnik-chervonenkis classes
Discrete Mathematics, 1981
On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
Theory of Probability and Its Applications, 1971