Sciweavers

ICML
1991
IEEE

Constructive Induction in Knowledge-Based Neural Networks

13 years 7 months ago
Constructive Induction in Knowledge-Based Neural Networks
Artificial neural networks have proven to be a successful, general method for inductive learning from examples. However, they have not often been viewed in terms of constructive induction. We describe a method for using a knowledgebased neural network of the kind created by the KBANN algorithmas the basis of a system forconstructive induction. After training,we extract two types of rules from a network: modified versions of the rules initially provided to the knowledgebased neural network, and rules which describe newly constructed features. Our experiments show that the extracted rules are more accurate, at classifying novel examples, than the trained network from which the rules are extracted.
Geoffrey G. Towell, Mark Craven, Jude W. Shavlik
Added 27 Aug 2010
Updated 27 Aug 2010
Type Conference
Year 1991
Where ICML
Authors Geoffrey G. Towell, Mark Craven, Jude W. Shavlik
Comments (0)