A hybrid connectionist, symbolic learning system

Authors:
Lawrence O. Hall;Steve G. Romaniuk
Affiliations:
Department of Computer Science and Engineering, University of South Florida, Tampa, Fl;Department of Computer Science and Engineering, University of South Florida, Tampa, Fl
Venue:
AAAI'90 Proceedings of the eighth National conference on Artificial intelligence - Volume 2
Year:
1990

Citing 6
Cited 0

A guide to expert systems

A guide to expert systems
MULTILISP: a language for concurrent symbolic computation

ACM Transactions on Programming Languages and Systems (TOPLAS)
Fuzzy mathematical techniques with applications

Fuzzy mathematical techniques with applications
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations
Backpropagation neural networks for fuzzy logic

Information Sciences: an International Journal
An empirical comparison of pattern recognition, neural nets, and machine learning classification methods

IJCAI'89 Proceedings of the 11th international joint conference on Artificial intelligence - Volume 1

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes the learning part of a system which has been developed to provide expert systems capability augmented with learning. The learning scheme is a hybrid connectionist, symbolic one. A network representation is used. Learning may be done incrementally and requires only one pass through the data set to be learned. Attribute, value pairs are supported as a variable implementation. Variables are represented by groups of connected cells in the network. The learning algorithm is described and an example given. Current results are discussed, which include learning the well-known Iris data set. The results show that the system has promise.