The DOI matches its Crossref record; 37 of the 37 references it cites were found in a registry or an index.
Using additive noise in back-propagation training
Abstract
The possibility of improving the generalization capability of a neural network by introducing additive noise to the training samples is discussed. The network considered is a feedforward layered neural network trained with the back-propagation algorithm. Back-propagation training is viewed as nonlinear least-squares regression and the additive noise is interpreted as generating a kernel estimate of the probability density that describes the training vector distribution. Two specific application types are considered: pattern classifier networks and estimation of a nonstochastic mapping from data corrupted by measurement errors. It is not proved that the introduction of additive noise to the training vectors always improves network generalization. However, the analysis suggests mathematically justified rules for choosing the characteristics of noise if additive noise is used in training. Results of mathematical statistics are used to establish various asymptotic consistency results for the proposed method. Numerical simulations support the applicability of the training method.
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 Internal Representations by Error Propagation
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1985) · doi:10.21236/ada164453 · Cited by 16,172
Parallel Distributed Processing: Explorations in the Microstructure of Cognition: Foundations
Rumelhart, D. E., McClelland, J. L., & AU (1986) · doi:10.7551/mitpress/5236.001.0001 · Cited by 15,686
On Estimation of a Probability Density Function and Mode
Parzen, E. (1962) · The Annals of Mathematical Statistics · doi:10.1214/aoms/1177704472 · Cited by 10,585
Density Estimation for Statistics and Data Analysis
(1986) · Springer eBooks · doi:10.1007/978-1-4899-3324-9 · Cited by 8,525
The Art of Computer Programming
Whitesides, G. E. (1970) · Nuclear Science and Engineering · doi:10.13182/nse70-a19705 · Cited by 6,008
Remarks on Some Nonparametric Estimates of a Density Function
Rosenblatt, M. (1956) · The Annals of Mathematical Statistics · doi:10.1214/aoms/1177728190 · Cited by 4,547
Specht, D. F. (1990) · Neural Networks · doi:10.1016/0893-6080(90)90049-q · Cited by 3,762
Devijver, P. A., & Kittler, J. (1982) · Prentice-Hall International eBooks · Cited by 2,910
Advances in Neural Information Processing Systems 5
Zemel, R. S., Williams, C. K. I., & Mozer, M. C. (1993) · Cited by 1,896
Asymptotic Properties of Non-Linear Least Squares Estimators
Jennrich, R. I. (1969) · The Annals of Mathematical Statistics · doi:10.1214/aoms/1177697731 · Cited by 1,327
Cited by
Caruana, R. (1997) · Machine Learning · doi:10.1023/a:1007379606734 · Cited by 6,636
Multitask Learning: A Knowledge-Based Source of Inductive Bias
Caruana, R. A. (1993) · Machine Learning Proceedings 1993 · doi:10.1016/b978-1-55860-307-3.50012-5 · Cited by 679
Caruana, R. (1998) · Learning to Learn · doi:10.1007/978-1-4615-5529-2_5 · Cited by 577
The Effects of Adding Noise During Backpropagation Training on a Generalization Performance
An, G. (1996) · Neural Computation · doi:10.1162/neco.1996.8.3.643 · Cited by 475
Wang, C., & Hill, D. J. (2006) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2005.860843 · Cited by 470
Large-Scale Optical Neural Networks Based on Photoelectric Multiplication
Hamerly, R., Bernstein, L., Sludds, A., Soljačić, M., & Englund, D. (2019) · Physical Review X · doi:10.1103/physrevx.9.021032 · Cited by 388
The significance of artificial intelligence in drug delivery system design
Hassanzadeh, P., Atyabi, F., & Dinarvand, R. (2019) · Advanced Drug Delivery Reviews · doi:10.1016/j.addr.2019.05.001 · Cited by 305
Piotrowski, A. P., & Napiorkowski, J. J. (2013) · Journal of Hydrology · doi:10.1016/j.jhydrol.2012.10.019 · Cited by 257
Enhanced MLP performance and fault tolerance resulting from synaptic weight noise during training
Murray, A. F., & Edwards, P. J. (1994) · IEEE Transactions on Neural Networks · doi:10.1109/72.317730 · Cited by 201
A neural network ensemble method with jittered training data for time series forecasting
Zhang, G. P. (2007) · Information Sciences · doi:10.1016/j.ins.2007.06.015 · Cited by 196
Loss of plasticity in deep continual learning
Dohare, S., Hernandez-Garcia, J. F., Lan, Q., Rahman, P., Mahmood, A. R., & Sutton, R. S. (2024) · Nature · doi:10.1038/s41586-024-07711-7 · Cited by 172
“The main benefits of adding noise have been reported to be avoiding overfitting and improving training performance 123–125 .”
Noise Injection: Theoretical Prospects
Grandvalet, Y., Canu, S., & Boucheron, S. (1997) · Neural Computation · doi:10.1162/neco.1997.9.5.1093 · Cited by 147
“f; t/ with respect to weights and time has full rank; thus, by the implicit function theorem in its surjective form ( Hirsch, 1976, p. 214 ), there exists a neighborhood of . f † ; 0/, 1100 Yves Grandvalet, St´ ephane Canu, and St´ ephane Boucheron”
BackgroundMethod
Metadata
- Authors
- Holmstrom, L., & Koistinen, P.
- Venue
- IEEE Transactions on Neural Networks
- Published
- 1992
- Volume
- 3
- Issue
- 1
- Pages
- 24-38
- ISSN
- 1045-9227 (ISSN-L)
- OpenAlex
- W2098874108
- Cited by
- 355
- References
- 37
- FWCI
- 12.07
- 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.