Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 170

The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.

ANN-DT: an algorithm for extraction of decision trees from artificial neural networks

Schmitz, G.P.J., Aldrich, C., Gouws, F.S.·1999·IEEE Transactions on Neural Networks

Abstract

Although artificial neural networks can represent a variety of complex systems with a high degree of accuracy, these connectionist models are difficult to interpret. This significantly limits the applicability of neural networks in practice, especially where a premium is placed on the comprehensibility or reliability of systems. A novel artificial neural-network decision tree algorithm (ANN-DT) is therefore proposed, which extracts binary decision trees from a trained neural network. The ANN-DT algorithm uses the neural network to generate outputs for samples interpolated from the training data set. In contrast to existing techniques, ANN-DT can extract rules from feedforward neural networks with continuous outputs. These rules are extracted from the neural network without making assumptions about the internal structure of the neural network or the features of the data. A novel attribute selection criterion based on a significance analysis of the variables on the neural-network output is examined. It is shown to have significant benefits in certain cases when compared with the standard criteria of minimum weighted variance over the branches. In three case studies the ANN-DT algorithm compared favorably with CART, a standard decision tree algorithm.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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

Integrity signals

Registry

Crossref · 10.1109/72.809084

Cites

3 of 3 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.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

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 3 references

Research works printed but not linked: 30

  1. nash, 1994, the population biology of abalone (haliotis species) in tasmania—i: blacklip abalone (<emph>h. rubra</emph>) from the north coast and islands of bass strait, Sea Fisheries Division
  2. 10.1023/A:1022604100933 · DOI · Paper page
  3. hays, 1988, Statistics
  4. 10.2307/2528823 · DOI · Paper page
  5. 10.1016/B978-1-55860-200-7.50040-4 · DOI
  6. 10.1109/21.398685 · doi:10.1109/21.398685
  7. thrun, 1994, Extracting provable correct rules from artificial neural networks
  8. thrun, 1995, extracting rules from artificial neural networks with distributed representation, Advances in neural information processing systems, 7
  9. pop, 1994, ruleng: extracting rules from a trained artificial neural network by stepwise negation, QUT NRC
  10. 10.1109/ICNN.1988.23855 · DOI · Paper page
  11. 10.1109/3477.484442 · DOI
  12. tickle, 1994, dedec: decision detection by rule extraction from neural networks, QUT NRC
  13. seisto, 1992, automated knowledge acquisition of rules with continuously valued attributes, Proc 12th Int Conf Expert Syst Applicat, 645
  14. masters, 1993, Practical Neural Network Recipes in C++
  15. craven, 1996, extracting tree structured representations of trained networks, Advances in Neural Information Processing Systems 8
  16. 10.1016/S0893-6080(98)00104-X · doi:10.1016/s0893-6080(98)00104-x
  17. breiman, 1984, Classification and Regression Trees
  18. 10.1162/neco.1989.1.2.281 · DOI · Paper page
  19. quinlan, 1993, C4 5 Programs for Machine Learning
  20. 10.1016/B978-1-55860-335-6.50013-1 · DOI · Paper page
  21. krzanowski, 1995, Kendall s Library of Statistics 2 Multivariate Analysis Part 2
  22. fu, 1991, rule learning by searching on adapted nets, Proc 9th Nat Conf Artificial Intell, 590
  23. 10.1007/BF00993103 · DOI · Paper page
  24. gallant, 1993, Neural Network Learning and Expert Systems, 10.7551/mitpress/4931.001.0001 · DOI · Paper page
  25. haykin, 1994, Neural Networks A Comprehensive Foundation
  26. aldrich, 1997, characterization of process systems with decision trees extracted from neural network models, Proc 5th European Congr Intell Syst Soft Comput, 2163
  27. rumelhart, 1986, Parallel Distribution Processing Exploration in the Microstructure of Cognition 1, 10.7551/mitpress/5236.001.0001 · DOI · Paper page
  28. werbos, 1974, Beyond Regression New Tools for Prediction and Analysis in the Behavioral Sciences
  29. broomhead, 1988, multivariable functional interpolation and adaptive networks, Complex Syst 2, 321
  30. powel, 1985, radial basis functions for multivariable interpolation: a review, IMA Conf Algorithms Approximation Functions and Data, 143

Cited by

See all 170

Metadata

Authors
Schmitz, G. P. J., Aldrich, C., & Gouws, F. S.
Venue
IEEE Transactions on Neural Networks
Published
1999
Volume
10
Issue
6
Pages
1392-1401
ISSN
1045-9227 (ISSN-L)
OpenAlex
W2158599326
Cited by
170
References
3
FWCI
7.61
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: ANN-DT: an algorithm for extraction of decision trees from artificial neural networks. https://app.cochat.ai/papers/10.1109/72.809084
The paper
Schmitz, G. P. J., Aldrich, C., & Gouws, F. S. (1999). ANN-DT: an algorithm for extraction of decision trees from artificial neural networks. IEEE Transactions on Neural Networks. https://doi.org/10.1109/72.809084

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.