The DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.
Optimal Brain Surgeon and general network pruning
Abstract
The use of information from all second-order derivatives of the error function to perform network pruning (i.e., removing unimportant weights from a trained network) in order to improve generalization, simplify networks, reduce hardware or storage requirements, increase the speed of further training, and, in some cases, enable rule extraction, is investigated. The method, Optimal Brain Surgeon (OBS), is significantly better than magnitude-based methods and Optimal Brain Damage, which often remove the wrong weights. OBS, permits pruning of more weights than other methods (for the same error on the training set), and thus yields better generalization on test data. Crucial to OBS is a recursion relation for calculating the inverse Hessian matrix H/sup -1/ from training data and structural information of the set. OBS deletes the correct weights from a trained XOR network in every case.>
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
Introduction to the theory of neural computation
(1994) · Neural Networks · doi:10.1016/0893-6080(94)90014-0 · Cited by 6,401
Modeling by shortest data description
Rissanen, J. (1978) · Automatica · doi:10.1016/0005-1098(78)90005-5 · Cited by 6,011
(1989) · Cited by 3,214
Parallel Networks that Learn to Pronounce English Text
B, T. J. S. A. (1987) · Cited by 1,514
(1993) · CaltechAUTHORS (California Institute of Technology) · Cited by 1,498
The MONK's problems: A Performance Comparison of Different Learning Algorithms
Thrun, S., Bala, J. W., Bloedorn, E., Bratko, I., Cestnik, B., Cheng, J. Q., Jong, K. A. D., Džeroski, S., Fisher, D., Fahlman, S. E., et al. (1991) · doi:10.13021/mars/3370 · Cited by 445
Interpretation of Artificial Neural Networks: Mapping Knowledge-Based Neural Networks into Rules
Towell, G. G., & SHAVLIK, J. W. (1991) · neural information processing systems · Cited by 98
A Frobenius approximation reduction method (FARM) for determining optimal number of hidden units
Kung, S., & Hu, Y. (2002) · 2022 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.1991.155331 · Cited by 29
Cited by
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
Frankle, J., & Carbin, M. (2018) · arXiv · doi:10.48550/arxiv.1803.03635 · Cited by 1,529
(1993) · CaltechAUTHORS (California Institute of Technology) · Cited by 1,498
A survey of modern deep learning based object detection models
Zaidi, S. S. A., Ansari, M. S., Aslam, A., Kanwal, N., Asghar, M., & Lee, B. (2022) · Digital Signal Processing · doi:10.1016/j.dsp.2022.103514 · Cited by 977
CondenseNet: An Efficient DenseNet Using Learned Group Convolutions
Huang, G., Liu, S., Maaten, L. V. D., & Weinberger, K. Q. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00291 · Cited by 904
Neural Networks and Deep Learning
Theodoridis, S. (2015) · Machine Learning · doi:10.1016/b978-0-12-801522-3.00018-5 · Cited by 900
Metadata
- Authors
- Hassibi, B., Stork, D. G., & Wolff, G. J.
- Venue
- IEEE International Conference on Neural Networks
- Publisher
- IEEE
- Published
- 2002-12-30
- Pages
- 293-299
- ISSN
- 1098-7576 (ISSN-L)
- OpenAlex
- W2156150815
- Cited by
- 597
- References
- 8
- FWCI
- 12.51
- Type
- conference paper
- 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: Optimal Brain Surgeon and general network pruning. https://app.cochat.ai/papers/10.1109/icnn.1993.298572
- The paper
- Hassibi, B., Stork, D. G., & Wolff, G. J. (2002). Optimal Brain Surgeon and general network pruning. IEEE International Conference on Neural Networks. https://doi.org/10.1109/icnn.1993.298572
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.