Generalization in a linear perceptron in the presence of noise
Open accessThe DOI matches its Crossref record.
Abstract
The authors study the evolution of the generalization ability of a simple linear perceptron with N inputs which learns to imitate a 'teacher perceptron'. The system is trained on p= alpha N example inputs drawn from some distribution and the generalization ability is measured by the average agreement with the teacher on test examples drawn from the same distribution. The dynamics may be solved analytically and exhibits a phase transition from imperfect to perfect generalization at alpha =1, when there are no errors (static noise) in the training examples. If the examples are produced by an erroneous teacher, overfitting is observed, i.e. the generalization error starts to increase after a finite time of training. It is shown that a weight decay of the same size as the variance of the noise (errors) on the teacher improves on the generalization and suppresses the overfitting. The generalization error as a function of time is calculated numerically for various values of the parameters. Finally dynamic noise in the training is considered. White noise on the input corresponds on average to a weight decay, and can thus improve generalization, whereas white noise on the weights or the output degrades generalization. Generalization is particularly sensitive to noise on the weights (for alpha (1) where it makes the error constantly increase with time, but this effect is also shown to be damped by a weight decay. Weight noise and output noise acts similarly above the transition at alpha =1.
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
Cited by
Faisal, A. A., Selen, L. P. J., & Wolpert, D. M. (2008) · Nature Reviews Neuroscience · doi:10.1038/nrn2258 · Cited by 2,883
(1992) · Cited by 1,405
If deep learning is the answer, what is the question?
Saxe, A., Nelli, S., & Summerfield, C. (2021) · Nature Reviews Neuroscience · doi:10.1038/s41583-020-00395-8 · Cited by 397
“4d) or when the number of data samples and model parameters both diverge towards infinity but their ratio is finite (the high-dimensional limit) 144,145 (Fig.”
BackgroundUsing additive noise in back-propagation training
Holmstrom, L., & Koistinen, P. (1992) · IEEE Transactions on Neural Networks · doi:10.1109/72.105415 · Cited by 355
Asymptotic statistical theory of overtraining and cross-validation
Amari, S., Murata, N., Muller, K.-R., Finke, M., & Yang, H. H. (1997) · IEEE Transactions on Neural Networks · doi:10.1109/72.623200 · Cited by 351
Metadata
- Authors
- Krogh, A., & Hertz, J. A.
- Venue
- Journal of Physics A: Mathematical and General
- Publisher
- IOP Publishing
- Published
- 1992-03-07
- Volume
- 25
- Issue
- 5
- Pages
- 1135-1147
- ISSN
- 0305-4470 (ISSN-L)
- 1361-6447
- OpenAlex
- W1964862779
- Cited by
- 116
- References
- 0
- FWCI
- 11.18
- Type
- journal article
- Language
- en
- Open access
- bronze
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: Generalization in a linear perceptron in the presence of noise. https://app.cochat.ai/papers/10.1088/0305-4470/25/5/020
- The paper
- Krogh, A., & Hertz, J. A. (1992). Generalization in a linear perceptron in the presence of noise. Journal of Physics A: Mathematical and General. https://doi.org/10.1088/0305-4470/25/5/020
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.