A new approach for testing artificial neural networks
Abstract
This paper presents progress on a new and novel testing approach for detecting interconnection deletion faults in electronic implementations of artificial neural networks (ANNs). The testing approach is based on an unusual transient behavior manifested by faulted ANNs showing better apparent performance than fault-free ANNs, when neurons are operated with low activation function gains. The result presented in this paper improves on prior results by requiring fewer test patterns.
References
[1]
M. Abramovici, M. A. Breuer, and A. D. Friedman. Digital Systems Testing and Testable Design. IEEE Press, New York, revised printing edition, 1990.
[2]
L. A. Belfore II and C. A. Fleischer. A test methodology for artificial neural networks. In Twenty-First Annual Conference of the IEEE Industrial Electronics Society, pages 1400-1405, Orlando, Florida, November 1995.
[3]
L. A. Belfore II and C. A. Fleischer. Testing recurrent artificial neural networks. In Proceedings of the 1995 IEEE Intenational Conference on Systems Man and Cybernetics, pages 462-467, Vancouver, British Columbia, Canada, October 1995.
[4]
J. Donald and L. Akers. An adaptive neural processing node. IEEE Transactions on Neural Networks, 4(3):413-426, May 1993.
[5]
W.-C. Fang, B. J. Sheu, O. T.-C. Chen, and J. Choi. A VLSI neural processor for image data compression using self-organizing networks. IEEE Transactions on Neural Networks , 3(3):506-517, May 1992.
[6]
D. B. I. Feltham and W. Maly. Physically realistic fault models for analog CMOS neural networks. IEEE Journal of Solid-State Circuits, 26(9):1223-1229, September 1991.
[7]
J. J. Hopfield. Neurons with graded response have collective computational properties like those of two-state neurons. Proceedings of the National Academy of Sciences USA, 81:3088-3092, May 1984.
[8]
W. Hsu, B. Sheu, and S. Gowda. Testing of analog neural array-processor chips. In IEEE International Conference on Computer Design, 1991, pages 118-121, 1991.
[9]
J. Hutchinson, C. Koch, J. Luo, and C. Mead. Computing motion using analog and binary resistive networks. Computer, 21(3):52-64, March 1988.
[10]
K. Madani. An analogue test technique for massively parallel integrated circuits and systems: An approach to neural networks circuits testing. Annals of Telecommunications, 48(11-12):537-545, 1993.
[11]
Maxim. Single/dual, ultra-fast, low-power precision TTL comparators. In MAXIM 1995 New Releases Data Book, Volume IV, pages 3-41-3-46. 1995.
[12]
V. Piuri, M. Sami, D. Sciuto, and R. Stefanelli. A behavioral approach to testability analysis for neural networks. Microprocessing and Microprogramming, 35(1-5):181-186, 1992.
Recommendations
A Low-Cost Fault-Tolerant Approach for Hardware Implementation of Artificial Neural Networks
ICCET '09: Proceedings of the 2009 International Conference on Computer Engineering and Technology - Volume 02Artificial Neural Networks (ANNs) are widely used in computational and industrial applications. As technology is developed the scale of hardware is progressively becoming smaller and the number of faults is increasing. Therefore, fault-tolerant methods ...
Noise Suppression by Artificial Neural Networks
AWICT 2017: Proceedings of the Second International Conference on Advanced Wireless Information, Data, and Communication TechnologiesIn this research paper, noise suppression ability of associative memories (e.g. Hopfield neural network) is briefly summarized. Motivated by this fact, noise suppression abilities of trained convolutional network are discussed. Introducing the concept ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
April 1997
ISBN:0818678100
Copyright © Copyright (c) 1997 Institute of Electrical and Electronics Engineers, Inc. All rights reserved.
Publisher
IEEE Computer Society
United States
Publication History
Published: 27 April 1997
Author Tags
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 08 Feb 2025