The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.
Symbolic interpretation of artificial neural networks
Abstract
Hybrid intelligent systems that combine knowledge-based and artificial neural network systems typically have four phases, involving domain knowledge representation, mapping of this knowledge into an initial connectionist architecture, network training and rule extraction, respectively. The final phase is important because it can provide a trained connectionist architecture with explanation power and validate its output decisions. Moreover, it can be used to refine and maintain the initial knowledge acquired from domain experts. In this paper, we present three rule extraction techniques. The first technique extracts a set of binary rules from any type of neural network. The other two techniques are specific to feedforward networks, with a single hidden layer of sigmoidal units. Technique 2 extracts partial rules that represent the most important embedded knowledge with an adjustable level of detail, while the third technique provides a more comprehensive and universal approach. A rule-evaluation technique, which orders extracted rules based on three performance measures, is then proposed. The three techniques area applied to the iris and breast cancer data sets. The extracted rules are evaluated qualitatively and quantitatively, and are compared with those obtained by other approaches.
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.
Integrity signals
Registry
Cites
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.
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
Survey and critique of techniques for extracting rules from trained artificial neural networks
Andrews, R., Diederich, J., & Tickle, A. B. (1995) · Knowledge-Based Systems · doi:10.1016/0950-7051(96)81920-4 · Cited by 1,225
Research works printed but not linked: 45
- taha, 1997, hybrid intelligent architecture and its application to water reservoir control, Int l J Smart Eng Systems, 1, 59
- 10.1016/0888-613X(91)90008-A · DOI · Paper page
- 10.1109/ICNN.1994.374419 · doi:10.1109/icnn.1994.374419
- 10.1109/ICNN.1994.374404 · doi:10.1109/icnn.1994.374404
- tickle, 1996, dedec: a methodology for extracting rules from trained artificial neural networks, Rules and Networks Proc Rule Extraction from Trained Artificial Neural Networks Workshop, 90
- 10.1142/S021800149700007X · doi:10.1142/s021800149700007x
- 10.1007/BF00993103 · DOI · Paper page
- 10.1109/21.214775 · DOI
- 10.1016/0004-3702(94)90105-8 · DOI · Paper page
- towell, 1990, refinement of approximate domain theories by knowledge-based artificial neural network, Proc Eighth Nat l Conf Artificial Intelligence, 861
- 10.1016/B978-1-55860-335-6.50013-1 · DOI · Paper page
- 10.1109/72.728352 · DOI · Paper page
- mcgarry, 1999, hybrid neural systems: from simple coupling to fully integrated neural networks, Neural Computing Surveys, 2, 62
- brayton, 1984, Logic Minimization Algorithm for VLSI Synthesis, 10.1007/978-1-4613-2821-6 · DOI
- andrews, 1995, inserting and extracting knowledge from constrained error backpropagation networks, Proc Sixth Australian Conf Neural Networks
- 10.1109/FUZZY.1999.793263 · DOI
- 10.1109/72.159069 · DOI · Paper page
- 10.1016/0364-0213(89)90012-8 · DOI
- glover, 1990, hybrid neural network and rule-based pattern recognition system capable of self-modification, Proc SPIE Application of Artificial Intelligence, 8, 290
- 10.1109/12.106218 · DOI · Paper page
- klinkenberg, 1996, rule set quality measures for inductive learning algorithms, Intelligent Eng Systems Through Artificial Neural Networks ANNIE, 6, 161
- kerber, 1992, chimerge: discretization of numeric attributes, Proc 10th Nat l Conf Artificial Intelligence AAAI, 123
- 10.1162/neco.1991.3.1.79 · DOI · Paper page
- giles, 1992, extracting and learning an unknown grammar with recurrent neural networks, Advances in Neural Information Processing Systems?4
- fu, 1994, Neural Networks in Computer Intelligence
- ghosh, 1994, structural adaptation and generalization in supervised feed-forward networks, J Artificial Neural Networks, 1, 431
- 10.1080/09540099308915704 · doi:10.1080/09540099308915704
- 10.1287/opre.43.4.570 · DOI · Paper page
- optiz, 1993, heuristically expanding knowledge-based neural network, Proc 13th Int l Joint Conf Artificial Intelligence, 512
- ourston, 1990, changing the rules: a comprehensive approach to theory refinement, Proc Eighth Nat l Conf Artificial Intelligence, 815
- quinlan, 1992, C4 5 Programs for Machine Learning
- ramachandran, 1997, theory refinement of bayesian networks with hidden variables, "Theory Refinement of Bayesian Networks with Hidden Variables "
- mcmillan, 1991, the connectionist scientist game: rule extraction and refinement in a neural network, Proc 13th Ann Conf Cognitive Science Soc
- mendenhall, 1979, Introduction to Probability and Statistics
- 10.1016/0893-6080(95)00086-0 · DOI · Paper page
- 10.1109/TAI.1995.479783 · DOI · Paper page
- 10.1109/ICNN.1988.23855 · DOI · Paper page
- schlimmer, 1996, concept acquisition through representational adjustment, "Concept Acquisition Through Representational Adjustment "
- ruddel, 1985, espresso-mv: algorithms for multiple-valued logic minimization, Proc Cust Int l Circ Conf
- taha, 1995, a hybrid intelligent architecture for refining input characterization and domain knowledge, Proc World Congress on Neural Networks (WCNN), 2, 284
- taha, 1997, a hybrid intelligent architecture for revising domain knowledge, "A Hybrid Intelligent Architecture for Revising Domain Knowledge "
- setiono, 1995, understanding neural networks via rule extraction, Proc 14th Int l Joint Conf Artificial Intelligence (IJCAI), 480
- 10.1109/2.485895 · DOI · Paper page
- sestito, 1995, automated knowledge acquisition of rules with continuously valued attributes, Proc 12th Int l Conf Expert Systems and Their Applications (AVIGNON), 645
- 10.1016/0933-3657(95)00019-4 · doi:10.1016/0933-3657(95)00019-4
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
“Multi-Layer Neural Networks Explanation by simplification Rule-based learner: [82, 83, 147, 148, 246, 247, 248, 249, 250, 251]”
Explaining Explanations: An Overview of Interpretability of Machine Learning
Gilpin, L. H., Bau, D., Yuan, B. Z., Bajwa, A., Specter, M., & Kagal, L. (2018) · 2018 IEEE 5th International Conference on Data Science and Advanced Analytics (DSAA) · doi:10.1109/dsaa.2018.00018 · Cited by 2,507
Ali, S., Abuhmed, T., El-Sappagh, S., Muhammad, K., Alonso-Moral, J. M., Confalonieri, R., Guidotti, R., Del Ser, J., Díaz-Rodríguez, N., & Herrera, F. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.101805 · Cited by 1,762
Credit rating analysis with support vector machines and neural networks: a market comparative study
Huang, Z., Chen, H., Hsu, C.-J., Chen, W.-H., & Wu, S. (2004) · Decision Support Systems · doi:10.1016/s0167-9236(03)00086-1 · Cited by 1,017
Metadata
- Authors
- Taha, I. A., & Ghosh, J.
- Venue
- IEEE Transactions on Knowledge and Data Engineering
- Published
- 1999
- Volume
- 11
- Issue
- 3
- Pages
- 448-463
- ISSN
- 1041-4347 (ISSN-L)
- OpenAlex
- W2112649152
- Cited by
- 217
- References
- 1
- FWCI
- 12.61
- 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
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.