CoChat

Orthogonal Search-Based Rule Extraction (OSRE) for Trained Neural Networks: A Practical and Efficient Approach

Etchells, T.A., Lisboa, P.J.G. · 2006 · IEEE Transactions on Neural Networks
Cited by 99

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/tnn.2005.863472

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.

A few free checks a day · papers already verified open instantly · results are public

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

  1. 10.1016/S0893-6080(01)00111-3 · DOI · Paper page
  2. Pop, 1994, RULENEG: Extracting rules from a trained ANN by stepwise negation
  3. Lisboa, 2000, Minimal MLPS do not model the XOR logic, Neurocomput. Rapid Commun., 48, 1033
  4. Taha, 1996, Three techniques for extracting rules from feedforward networks, Intell. Eng. Syst. Through Artif. Neural Networks, 6, 23
  5. 10.1109/72.839008 · DOI · Paper page
  6. 10.1007/BF00993103 · DOI · Paper page
  7. 10.1016/S0925-2312(97)00038-6 · DOI
  8. 10.1016/S0004-3702(00)00077-1 · DOI · Paper page
  9. 10.1109/TNN.2004.836249 · DOI
  10. 10.1109/TNN.2005.849843 · DOI
  11. 10.1109/TNN.2004.837585 · DOI
  12. 10.1109/TNN.2004.837785 · doi:10.1109/tnn.2004.837785
  13. 10.1109/TNN.2004.836200 · DOI
  14. 10.1109/TNN.2003.820557 · doi:10.1109/tnn.2003.820557
  15. Thrun, 1991, The MONK’s Problems: A performance comparison of different learning algorithms
  16. Wisconsin Breast Cancer Database
  17. 2002, Derive 5.06 A Computer Algebra System Texas Instruments, Inc.
  18. 10.1016/S0933-3657(99)00041-X · DOI
  19. 10.1016/S0925-2312(97)00038-6 · DOI
  20. Cross, Private communication
  21. Data mining analysis
  22. Klose, Some approaches to improve the interpretability of neuro-fuzzy classifiers, 629

Cited by

See all 99

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Orthogonal Search-Based Rule Extraction (OSRE) for Trained Neural Networks: A Practical and Efficient Approach. https://app.cochat.ai/papers/10.1109/tnn.2005.863472
The paper
Etchells, T. A., & Lisboa, P. J. G. (2006). Orthogonal Search-Based Rule Extraction (OSRE) for Trained Neural Networks: A Practical and Efficient Approach. IEEE Transactions on Neural Networks. https://doi.org/10.1109/tnn.2005.863472

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.