Neural methods of knowledge extraction

Neural methods of knowledge extraction

0.00 Avg rating0 Votes
Article ID: iaor2009631
Country: Poland
Volume: 29
Issue: 4
Start Page Number: 997
End Page Number: 1017
Publication Date: Jan 2000
Journal: Control and Cybernetics
Authors: , , ,
Keywords: knowledge management
Abstract:

Contrary to the common opinion, neural networks may be used for knowledge extraction. Recently, a new methodology of logical rule extraction, optimization and application of rule-based systems has been described. C-MLP2LN algorithm, based on constrained multilayer perception network, is described here in details and the dynamics of a transition from neural to logical system illustrated. The algorithm handles real-valued features, determining appropriate linguistic variables or membership functions as a part of the rule extraction process.

Reviews

Required fields are marked *. Your email address will not be published.