Orthogonal Search-Based Rule Extraction (OSRE) for Trained Neural Networks: A Practical and Efficient Approach
- 6 March 2006
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 17 (2) , 374-384
- https://doi.org/10.1109/tnn.2005.863472
Abstract
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.Keywords
This publication has 13 references indexed in Scilit:
- Are Artificial Neural Networks White Boxes?IEEE Transactions on Neural Networks, 2005
- Uncertainty of Data, Fuzzy Membership Functions, and Multilayer PerceptronsIEEE Transactions on Neural Networks, 2005
- Heterogeneous Fuzzy Logic Networks: Fundamentals and Development StudiesIEEE Transactions on Neural Networks, 2004
- Encoding Nondeterministic Fuzzy Tree Automata Into Recursive Neural NetworksIEEE Transactions on Neural Networks, 2004
- A Neuro-Fuzzy Scheme for Simultaneous Feature Selection and Fuzzy Rule-Based ClassificationIEEE Transactions on Neural Networks, 2004
- Minimal MLPs do not model the XOR logicNeurocomputing, 2002
- Extracting rules from trained neural networksIEEE Transactions on Neural Networks, 2000
- Generating concise and accurate classification rules for breast cancer diagnosisArtificial Intelligence in Medicine, 2000
- NeuroLinear: From neural networks to oblique decision rulesNeurocomputing, 1997
- Extracting refined rules from knowledge-based neural networksMachine Learning, 1993