Article

Free access

Continuous learning: a design methodology for fault-tolerant neural networks

Author:

Vincenzo PiuriAuthors Info & Claims

IEA/AIE '90: Proceedings of the 3rd international conference on Industrial and engineering applications of artificial intelligence and expert systems - Volume 2

Pages 1019 - 1029

https://doi.org/10.1145/98894.99116

Published: 01 June 1990 Publication History

Abstract

Fault tolerance in artificial neural networks is an important feature, in particular when the application is critical or when maintenance is difficult. This paper presents a general design methodology for designing fault-tolerant architectures, starting from the behavioral description of the nominal network and from the nominal algorithm. The behavioral level is considered to detect errors due to hardware faults, while system survival is guaranteed by the reactivation of learning mechanisms of the nominal network. An example of the use of this methodology is presented and evaluated.

References

[1]

J.A. Abraham, P. Banerjee, C.Y. Chen, W.K. Fuchs, S.Y. Kuo, A.L. Reddy, 'Fault tolerance techniques for systolic arrays', IEEE Comp. Magazine, 1987

Digital Library

[2]

J.A. Abraham, W.K. Fuchs, 'Fault and error models for VLSI', Proc. iEEE, May 1986

[3]

D.H. Ackley, G.E. Hinton, T.J. Sejnowskl, ' A learning algorithm for Boltzmann machines", Cognitive Science, 1985

[4]

J.A. Anderson, 'Cognitive and psychological computation with neural models', IEEE Trans. on $ysterns, Man and Cybernetics, 1983

[5]

J.A. Anderson, E. Rosenfeld, editors, Neurocomputing: foundations of research, The MIT Press, 1988

Digital Library

[6]

D.Z. Anderson, editor, Neural information processin9 systems, The American Institute of Physics, 1988

[7]

F. Diatante, M. Sami, R. Stefanelli, G. Storti Gajani, 'A configurabh array architecture for WSI implementation of neural nets~, Proc. IPCCC'90, Phoe nix, 1990

[8]

G.E. Hinton, J.L. McClelland, 'Leraning represenrations by recirculation', IEEE Proc. on Neural Information Processing Systems, 1988

[9]

J.J. Hopfield, "Neural networks and physical systems with emergen collective computational abilities", Pro~. of the National Academic Sciences of USA, April 1982

[10]

T. Kohonen, Self organisation and associative memory, Springer-Verlag, 1984

Digital Library

[11]

M.L. Minsky, S.S. Seymour, Perceptrons, The MIT Press, 1969

[12]

R. Negrini, M.G. Sami, R.Stefanelli, Fault Tolerance through reconfiguratioa in VLSI and WSI arrays, The MIT Press, 1989

[13]

D.E. Rumelhart, G.E. Hinton, J.L. McClelland, Learning internal representations by error propsgation', Parallel and distributed processing, vol. 1, The MiT Press, 1986

Digital Library

[14]

D.P. Siewiorek, R.S. Swarz, The theory and practice of reliable system design, Digital Press, 1982

[15]

B. Widrow, M. Hoff, ' Adaptive switching circuits', IRE WESCON Convention, 1960

Cited By

Ekong DAbd-El-Barr MWood H(1993)Fault tolerant neural networks for control systemsIEEE WESCANEX 93 Communications, Computers and Power in the Modern Environment - Conference Proceedings10.1109/WESCAN.1993.270586(269-275)Online publication date: 1993
https://doi.org/10.1109/WESCAN.1993.270586
Ekong DAdb-El-Barr MWood H(1993)Design of fault tolerant neurocontrollers using immunization techniqueIEEE International Conference on Neural Networks10.1109/ICNN.1993.298744(1295-1300)Online publication date: 1993
https://doi.org/10.1109/ICNN.1993.298744

Index Terms

Continuous learning: a design methodology for fault-tolerant neural networks
1. Computer systems organization
  1. Architectures
    1. Other architectures
      1. Reconfigurable computing
      2. Self-organizing autonomic computing
2. Computing methodologies
  1. Artificial intelligence
    1. Philosophical/theoretical foundations of artificial intelligence
  2. Machine learning

Recommendations

Fault tolerant training of neural networks for learning vector quantization
ICONIP'06: Proceedings of the 13th international conference on Neural Information Processing - Volume Part II

The learning vector quantization(LVQ) is a model of neural networks, and it is used for complex pattern classifications in which typical feedforward networks don't give a good performance. Fault tolerance is an important feature in the neural networks, ...
Learning Algorithms Which Make Multilayer Neural Networks Multiple-Weight-and-Neuron-Fault Tolerant

Two simple but useful methods, called the deep learning methods, for making multilayer neural networks tolerant to multiple link-weight and neuron-output faults, are proposed. The methods make the output errors in learning phase smaller than those in ...
Activation Function Manipulation for Fault Tolerant Feedforward Neural Networks
ATS '99: Proceedings of the 8th Asian Test Symposium

We propose a learning algorithm to enhance the fault tolerance of feedforward neural networks (NNs for short) by manipulating the gradient of sigmoid activation function of the neuron. For the output layer, we employ the function with the relatively ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Conferences

IEA/AIE '90: Proceedings of the 3rd international conference on Industrial and engineering applications of artificial intelligence and expert systems - Volume 2

June 1990

591 pages

ISBN:0897913728

DOI:10.1145/98894

Chairman:
Manton M. Matthews

Copyright © 1990 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

SIGAI: ACM Special Interest Group on Artificial Intelligence

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 01 June 1990

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Qualifiers

Article

Conference

IEA/AEI-90

Sponsor:

SIGAI

IEA/AEI-90: 3rd International Conference on Industrial & Engineering Applications of Artificial Intelligence & Expert Systems

South Carolina, Charleston, USA

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

2
Total Citations
View Citations
806
Total Downloads

Downloads (Last 12 months)37
Downloads (Last 6 weeks)11

Reflects downloads up to 18 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

Ekong DAbd-El-Barr MWood H(1993)Fault tolerant neural networks for control systemsIEEE WESCANEX 93 Communications, Computers and Power in the Modern Environment - Conference Proceedings10.1109/WESCAN.1993.270586(269-275)Online publication date: 1993
https://doi.org/10.1109/WESCAN.1993.270586
Ekong DAdb-El-Barr MWood H(1993)Design of fault tolerant neurocontrollers using immunization techniqueIEEE International Conference on Neural Networks10.1109/ICNN.1993.298744(1295-1300)Online publication date: 1993
https://doi.org/10.1109/ICNN.1993.298744

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Figures

Tables

Media

View Table of Conten