Orthogonal Search-Based Rule Extraction (OSRE) for Trained Neural Networks: A Practical and Efficient Approach
The DOI matches its Crossref record.
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
No references could be resolved yet.
Research works printed but not linked: 22
- 10.1016/S0893-6080(01)00111-3 · DOI · Paper page
- Pop, 1994, RULENEG: Extracting rules from a trained ANN by stepwise negation
- Lisboa, 2000, Minimal MLPS do not model the XOR logic, Neurocomput. Rapid Commun., 48, 1033
- Taha, 1996, Three techniques for extracting rules from feedforward networks, Intell. Eng. Syst. Through Artif. Neural Networks, 6, 23
- 10.1109/72.839008 · DOI · Paper page
- 10.1007/BF00993103 · DOI · Paper page
- 10.1016/S0925-2312(97)00038-6 · DOI
- 10.1016/S0004-3702(00)00077-1 · DOI · Paper page
- 10.1109/TNN.2004.836249 · DOI
- 10.1109/TNN.2005.849843 · DOI
- 10.1109/TNN.2004.837585 · DOI
- 10.1109/TNN.2004.837785 · doi:10.1109/tnn.2004.837785
- 10.1109/TNN.2004.836200 · DOI
- 10.1109/TNN.2003.820557 · doi:10.1109/tnn.2003.820557
- Thrun, 1991, The MONK’s Problems: A performance comparison of different learning algorithms
- Wisconsin Breast Cancer Database
- 2002, Derive 5.06 A Computer Algebra System Texas Instruments, Inc.
- 10.1016/S0933-3657(99)00041-X · DOI
- 10.1016/S0925-2312(97)00038-6 · DOI
- Cross, Private communication
- Data mining analysis
- Klose, Some approaches to improve the interpretability of neuro-fuzzy classifiers, 629
Cited by
Arrieta, A. B., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., García, S., Gil-López, S., Molina, D., Benjamins, R., et al. (2019) · arXiv · doi:10.48550/arxiv.1910.10045 · Cited by 11,321
Barredo Arrieta, A., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., Garcia, S., Gil-Lopez, S., Molina, D., Benjamins, R., et al. (2020) · Information Fusion · doi:10.1016/j.inffus.2019.12.012 · Cited by 10,423
Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)
Adadi, A., & Berrada, M. (2018) · IEEE Access · doi:10.1109/access.2018.2870052 · Cited by 6,294
“the view of the underlying ANN is opaque, the Orthogonal Search-based Rule Extraction algorithm (OSRE) from [119] is a successful pedagogical methodology often applied in biomedicine.”
BackgroundA Survey on the Explainability of Supervised Machine Learning
Burkart, N., & Huber, M. F. (2021) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.12228 · Cited by 1,008
Applying Data Mining Techniques to e-Learning Problems
Castro, F., Vellido, A., Nebot, À., & Mugica, F. (2007) · Studies in Computational Intelligence · doi:10.1007/978-3-540-71974-8_8 · Cited by 276
Metadata
- Authors
- Etchells, T. A., & Lisboa, P. J. G.
- Venue
- IEEE Transactions on Neural Networks
- Published
- 2006-03
- Volume
- 17
- Issue
- 2
- Pages
- 374-384
- ISSN
- 1045-9227 (ISSN-L)
- OpenAlex
- W2116767760
- Cited by
- 99
- References
- 0
- FWCI
- 11.10
- Type
- journal article
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.