The DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Unsupervised adaptation to improve fault tolerance of neural network classifiers
Abstract
We investigate how to exploit the dynamics of unsupervised online learning rules for fault tolerance in neural network classifiers. We first design an adaptation mechanism that keeps neural network weights at a useful fixed point for classification problems. We then demonstrate the robustness of the system when the network inputs are subjected to faults.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“As demonstrated in [43], [44], as well as the results of this paper, the attractor states of the AHaH rule coincide with the maximum-margin solution.”
From AHaH Computing–From Metastable Switches to Attractors to Machine Learning (2014) · cites this paper as [43]
In the citing paper
“Using a kurtosis objective function, it can be shown that a plasticity rule of the following form emerges [43]:(5)where and are constants that control the relative contribution of Hebbian and anti-Hebbian plasticity, respectively.”
From AHaH Computing–From Metastable Switches to Attractors to Machine Learning (2014) · cites this paper as [43]
In the citing paper
“In 2004, Nugent et al. showed how the AHAH plasticity rule is derived via the minimization of a kurtosis objective function and used as the basis of self-organized fault tolerance in support vector machine network classifiers.”
From AHaH Computing–From Metastable Switches to Attractors to Machine Learning (2014) · cites this paper as [43]
In the citing paper
“It also follows that a system built of components locked in attractor states will spontaneously heal if damaged [43], [44].”
From AHaH Computing–From Metastable Switches to Attractors to Machine Learning (2014) · cites this paper as [43]
Citations
Cites
UCI Machine Learning Repository
Asuncion, A. (2007) · Medical Entomology and Zoology · Cited by 25,410
The Elements of Statistical Learning
Hastie, T., Friedman, J., & Tibshirani, R. (2001) · Springer Series in Statistics · doi:10.1007/978-0-387-21606-5 · Cited by 24,162
Independent Component Analysis
(2004) · Independent Component Analysis · doi:10.7551/mitpress/3717.003.0014 · Cited by 7,903
Independent Component Analysis
Hyvärinen, A., Karhunen, J., & Oja, E. (2001) · Wiley eBooks · doi:10.1002/0471221317 · Cited by 5,007
Simplified neuron model as a principal component analyzer
Oja, E. (1982) · Journal of Mathematical Biology · doi:10.1007/bf00275687 · Cited by 2,309 · cited 1×
“Oja [2] was one of the first to suggest this type of rule for finding interesting statistical structure in data.”
BackgroundThe “independent components” of natural scenes are edge filters
Bell, A. J., & Sejnowski, T. J. (1997) · Vision Research · doi:10.1016/s0042-6989(97)00121-1 · Cited by 2,201
Intrator, N., & Cooper, L. N. (1992) · Neural Networks · doi:10.1016/s0893-6080(05)80003-6 · Cited by 211
(2002) · Raven A Journal of Vexillology · doi:10.5840/raven2002/20039/1079 · Cited by 95
From here to there : future robust EHW technologies for large digital designs
Haddow, P. C., & van Remortel, P. (2002) · doi:10.1109/eh.2001.937966 · Cited by 12
Multimodality exploration by an unsupervised projection pursuit neural network
Dotan, Y., & Intrator, N. (1998) · IEEE Transactions on Neural Networks · doi:10.1109/72.668888 · Cited by 11
Cited by
AHaH Computing–From Metastable Switches to Attractors to Machine Learning
Nugent, M. A., & Molter, T. W. (2014) · PLoS ONE · doi:10.1371/journal.pone.0085175 · Cited by 55
“As demonstrated in [43,44], as well as the results of this paper, the attractor states of the AHaH rule coincide with the maximum-margin solution.”
BackgroundResultInfluentialAn FPGA Implementation of a Convolutional Auto-Encoder
Zhao, W., Jia, Z., Wei, X., & Wang, H. (2018) · Applied Sciences · doi:10.3390/app8040504 · Cited by 16
Nugent, M. A., Porter, R., & Kenyon, G. T. (2008) · Physica D: Nonlinear Phenomena · doi:10.1016/j.physd.2008.03.043 · Cited by 2
“Static Network Result Adaptive Network Result FAULTS INTRODUCED Time = 1 Time = 120 Nugent et al. 16 (Nugent et al., 2004).”
BackgroundMethodInfluentialSelf-citationAlippi, C., Roveri, M., & Vanini, G. (2009) · IGI Global eBooks · doi:10.4018/978-1-60566-026-4.ch527 · Cited by 2
“The robustness of neural networks with respect to hardware implementations were also studied in Hereford and Kuyucu (2005) and Nugent, Kenyon, and Porter (2004) where authors proposed evolutionary and adaptive approaches.”
Method
Metadata
- Authors
- Nugent, A., Kenyon, G., & Porter, R.
- Affiliations
- Los Alamos National Laboratory (US)
- ORCID
- Kenyon, G.
- Venue
- Proceedings. 2004 NASA/DoD Conference on Evolvable Hardware, 2004.
- Publisher
- IEEE
- Published
- 2004-11-12
- Pages
- 146-149
- OpenAlex
- W2103745410
- Cited by
- 4
- References
- 10
- Citations by year
- 2018: 1 · 2014: 1
- FWCI
- 0.00
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- NASA/DoD Conference on Evolvable Hardware (publishedVersion)
- Funders
- Los Alamos National Laboratory
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Physical Sciences › Engineering › Control and Systems Engineering › Fault Detection and Control Systems
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Keywords
- fault tolerance, neural network classifier, weight adaptation
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: Unsupervised adaptation to improve fault tolerance of neural network classifiers. https://app.cochat.ai/papers/10.1109/eh.2004.1310824
- The paper
- Nugent, A., Kenyon, G., & Porter, R. (2004). Unsupervised adaptation to improve fault tolerance of neural network classifiers. Proceedings. 2004 NASA/DoD Conference on Evolvable Hardware, 2004. https://doi.org/10.1109/eh.2004.1310824
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.