Eigenvalues of covariance matrices: Application to neural-network learning
The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.
Abstract
The learing time of a simple neural-network model is obtained through an analytic computation of the eigenvalue spectrum for the Hessian matrix, which describes the second-order properties of the objective function in the space of coupling coefficients. The results are generic for symmetric matrices obtained by summing outer products of random vectors. The form of the eigenvalue distribution suggests new techniques for accelerating the learning process, and provides a theoretical justification for the choice of centered versus biased state variables.
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
Learning representations by back-propagating errors
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986) · Nature · doi:10.1038/323533a0 · Cited by 31,892
Backpropagation Applied to Handwritten Zip Code Recognition
LeCun, Y., Boser, B., Denker, J. S., Henderson, D., Howard, R. E., Hubbard, W., & Jackel, L. D. (1989) · Neural Computation · doi:10.1162/neco.1989.1.4.541 · Cited by 11,891
Self-citationInfinite Number of Order Parameters for Spin-Glasses
Parisi, G. (1979) · Physical Review Letters · doi:10.1103/physrevlett.43.1754 · Cited by 1,140
Cited by
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
“This makes the mean input roughly zero and the variance roughly one, which accelerates learning [46].”
BackgroundSelf-citationFast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
Clevert, D.-A., Unterthiner, T., & Hochreiter, S. (2015) · arXiv · doi:10.48550/arxiv.1511.07289 · Cited by 4,513
“them (Desjardins et al., 2015). An alternative to centering is to push the mean activation toward zero by an appropriate activation function. Therefore tanhhas been preferred over logistic functions (LeCun et al., 1991; 1998). Recently “Leaky ReLUs” (LReLUs) that replace the negative part of the ReLU with a linear fun…”
BackgroundMethodInfluentialRandom Matrix Theory and Wireless Communications
Tulino, A. M., & Verdú, S. (2004) · Foundations and Trends™ in Communications and Information Theory · doi:10.1561/0100000001 · Cited by 2,034
GradientBased Learning Applied to Document Recognition
(2009) · Intelligent Signal Processing · doi:10.1109/9780470544976.ch9 · Cited by 1,135
Object Recognition with Gradient-Based Learning
LeCun, Y., Haffner, P., Bottou, L., & Bengio, Y. (1999) · Lecture Notes in Computer Science · doi:10.1007/3-540-46805-6_19 · Cited by 947
“This makes the mean input roughly 0, and the variance roughly 1 which accelerates learning [ 20 ].”
BackgroundSelf-citation
Metadata
- Authors
- Cun, Y. L., Kanter, I., & Solla, S. A.
- Venue
- Physical Review Letters
- Publisher
- American Physical Society (APS)
- Published
- 1991-05-06
- Volume
- 66
- Issue
- 18
- Pages
- 2396-2399
- ISSN
- 0031-9007 (ISSN-L)
- OpenAlex
- W1992774725
- Cited by
- 146
- References
- 3
- FWCI
- 3.77
- 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.