Orthogonal search-based rule extraction (OSRE) for trained neural networks: a practical and efficient approach

There is much interest in rule extraction from neural networks and a plethora of different methods have been proposed for this purpose. We discuss the merits of pedagogical and decompositional approaches to rule extraction from trained neural networks, and show that some currently used methods for b...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transaction on neural networks and learning systems 2006-03, Vol.17 (2), p.374-384
Main Authors: Etchells, T.A., Lisboa, P.J.G.
Format: Article
Language:English
Subjects:
Algorithms
Applied sciences
Artificial Intelligence
Boolean algebra
Boolean functions
Breast cancer
Computer science
control theory
systems
Computer Simulation
Connectionism. Neural networks
Data mining
Data visualization
Decision analysis
Decision Support Techniques
Etching
Exact sciences and technology
Extraction
Formalism
Law
Legal factors
Mathematical analysis
Mathematical models
Methodology
Models, Theoretical
Neural networks
Neural Networks (Computer)
Numerical Analysis, Computer-Assisted
Pattern Recognition, Automated - methods
rule extraction
Testing
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:There is much interest in rule extraction from neural networks and a plethora of different methods have been proposed for this purpose. We discuss the merits of pedagogical and decompositional approaches to rule extraction from trained neural networks, and show that some currently used methods for binary data comply with a theoretical formalism for extraction of Boolean rules from continuously valued logic. This formalism is extended into a generic methodology for rule extraction from smooth decision surfaces fitted to discrete or quantized continuous variables independently of the analytical structure of the underlying model, and in a manner that is efficient even for high input dimensions. This methodology is then tested with Monks' data, for which exact rules are obtained and to Wisconsin's breast cancer data, where a small number of high-order rules are identified whose discriminatory performance can be directly visualized.
ISSN:1045-9227
2162-237X
1941-0093
2162-2388
DOI:10.1109/TNN.2005.863472