A general framework for symbol and rule extraction in neural networks

We split the rule extraction task into a subsymbolic 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...

Full description

Saved in:
Bibliographic Details
Main Authors: Apolloni, B., Orovas, C., Taylor, J., Fellenz, W., Gielen, S., Westerdijk, M.
Format: Conference Proceeding
Language:English
Subjects:
Artificial intelligence
Artificial neural networks
Biological neural networks
Computer science
Data mining
Educational institutions
Filling
Intelligent networks
Mathematics
Neural networks
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We split the rule extraction task into a subsymbolic 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.
ISSN:1098-7576
1558-3902
DOI:10.1109/IJCNN.2000.857879