Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Cited by 166

The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.

Extracting rules from trained neural networks

Tsukimoto, H. · 2000 · IEEE Transactions on Neural Networks

Abstract

This paper presents an algorithm for extracting rules from trained neural networks. The algorithm is a decompositional approach which can be applied to any neural network whose output function is monotone such as sigmoid function. Therefore, the algorithm can be applied to multilayer neural networks, recurrent neural networks and so on. It does not depend on training algorithms, and its computational complexity is polynomial. The basic idea is that the units of neural networks are approximated by Boolean functions. But the computational complexity of the approximation is exponential, and so a polynomial algorithm is presented. The author has applied the algorithm to several problems to extract understandable and accurate rules. This paper shows the results for the votes data, mushroom data, and others. The algorithm is extended to the continuous domain, where extracted rules are continuous Boolean functions. Roughly speaking, the representation by continuous Boolean functions means the representation using conjunction, disjunction, direct proportion, and reverse proportion. This paper shows the results for iris data.

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 · 10.1109/72.839008

Cites

1 of 1 references verified0 citation errors · 0 not checkable

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

Show all 1 references

Research works printed but not linked: 19

  1. 10.1016/0893-6080(95)00086-0 · DOI · Paper page
  2. quinlan, 1993, C4 5 Programs for Machine Learning
  3. 10.1007/BF00993982 · doi:10.1007/bf00993982
  4. thurn, 1993, Extracting provably correct rules from artificial neural networks
  5. 10.1007/BF00993103 · DOI · Paper page
  6. tsukimoto, 1994, the discovery of propositions in noisy data, Machine Intelligence 13, 143, 10.1093/oso/9780198538509.003.0006 · doi:10.1093/oso/9780198538509.003.0006
  7. tsukimoto, 1994, the discovery of logical propositions in numerical data, AAAI 94 Wkshp Knowledge Discovery in Databases, 205
  8. tsukimoto, 1994, on continuously valued logical functions satisfying all axioms of classical logic, Syst Comput Japan, 25, 33
  9. tsukimoto, 1995, efficient algorithms for inductive learning—an application of multilinear functions to inductive learning, Machine Intelligence 14, 427
  10. tsukimoto, 1996, an algorithm for extracting propositions from trained neural networks using multilinear functions, Rules Networks Proc Rule Extraction Trained Artificial Neural Networks Wkshp AISB 96, 103
  11. 10.1016/B978-1-55860-307-3.50016-2 · DOI
  12. andrews, 1996, Rules and Networks Proc Rule Extraction Trained Artificial Neural Networks Wkshp AISB 96
  13. 10.1109/21.299696 · DOI · Paper page
  14. 10.1016/B978-1-55860-335-6.50013-1 · DOI · Paper page
  15. 10.1109/72.159060 · DOI
  16. 10.1016/0893-6080(96)83696-3 · DOI · Paper page
  17. andrews, 1994, rule extraction from a constrained error back propagation mlp, Proc 5th Australian Conf Neural Networks, 9
  18. 10.1145/174130.174138 · DOI · Paper page
  19. tsukimoto, 1997, extracting propositions from trained neural networks, Proc IJCAI-97, 1098

Cited by

Metadata

Authors
Tsukimoto, H.
Venue
IEEE Transactions on Neural Networks
Published
2000-03
Volume
11
Issue
2
Pages
377-389
ISSN
1045-9227 (ISSN-L)
OpenAlex
W2145470394
Cited by
166
References
1
FWCI
9.58
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.