A General Framework for Symbol and Rule Extraction in Neural Networks

Authors:
B. Apolloni;C. Orovas;J. Taylor;W. Fellenz;Stan Gielen;Machiel Westerdijk
Affiliations:
-;-;-;-;-;-
Venue:
IJCNN '00 Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 2 - Volume 2
Year:
2000

Citing 0
Cited 3

Neural Networks Letter: Intelligent initialization of resource allocating RBF networks

Neural Networks
Reinforcement learning for rule extraction from a labeled dataset

Cognitive Systems Research
From synapses to rules

Cognitive Systems Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

We split the rule extraction task in to a sub-symbolic and a symbolic phase and present a set of neural networks for filling the former. Under the two general commitments of: i) having a learning algorithm that is sensitive to feedback signals coming from the latter phase, and ii) extracting Boolean variables whose meaning is determined by the further symbolic processing, we introduce three unsupervised learning algorithms and show related numerical examples for a multilayer perceptron, recurrent neural networks, and a specially devised vector quantizer.