An Empirical Evaluation of Rule Extraction from Recurrent Neural Networks
Open accessThe DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.
Abstract
Rule extraction from black box models is critical in domains that require model validation before implementation, as can be the case in credit scoring and medical diagnosis. Though already a challenging problem in statistical learning in general, the difficulty is even greater when highly nonlinear, recursive models, such as recurrent neural networks (RNNs), are fit to data. Here, we study the extraction of rules from second-order RNNs trained to recognize the Tomita grammars. We show that production rules can be stably extracted from trained RNNs and that in certain cases, the rules outperform the trained RNNs.
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
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Sukhbaatar, S., Szlam, A., Weston, J., & Fergus, R. (2015) · arXiv · doi:10.48550/arxiv.1503.08895 · Cited by 1,345
Cited by
Explainable artificial intelligence: a comprehensive review
Minh, D., Wang, H. X., Li, Y. F., & Nguyen, T. N. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-021-10088-y · Cited by 983
Schwalbe, G., & Finzel, B. (2024) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-022-00867-8 · Cited by 328
Garcez, A. D., Gori, M., Lamb, L. C., Serafini, L., Spranger, M., & Tran, S. N. (2019) · arXiv · doi:10.48550/arxiv.1905.06088 · Cited by 175
“Most of them are discussed in the surveys [1, 24, 55].”
BackgroundOpening the AI Black Box: Distilling Machine-Learned Algorithms into Code
Michaud, E. J., Liao, I., Lad, V., Liu, Z., Mudide, A., Loughridge, C., Guo, Z. C., Kheirkhah, T. R., Vukelić, M., & Tegmark, M. (2024) · Entropy · doi:10.3390/e26121046 · Cited by 30
Extracting Weighted Finite Automata from Recurrent Neural Networks for Natural Languages
Wei, Z., Zhang, X., & Sun, M. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-17244-1_22 · Cited by 6
Metadata
- Authors
- Wang, Q., Zhang, K., Ororbia II, A. G., Xing, X., Liu, X., & Giles, C. L.
- Venue
- Neural Computation
- Publisher
- MIT Press
- Published
- 2018-09
- Volume
- 30
- Issue
- 9
- Pages
- 2568-2591
- ISSN
- 0899-7667 (ISSN-L)
- 1530-888X
- OpenAlex
- W2771330107
- Cited by
- 54
- References
- 2
- FWCI
- 5.23
- Type
- journal article
- Language
- en
- Open access
- green
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: An Empirical Evaluation of Rule Extraction from Recurrent Neural Networks. https://app.cochat.ai/papers/10.1162/neco_a_01111
- The paper
- Wang, Q., Zhang, K., Ororbia II, A. G., Xing, X., Liu, X., & Giles, C. L. (2018). An Empirical Evaluation of Rule Extraction from Recurrent Neural Networks. Neural Computation. https://doi.org/10.1162/neco_a_01111
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.