Cited By
View all- Sibai FKulkarni S(1997)A Time-Multiplexed Reconfigurable NeuroprocessorIEEE Micro10.1109/40.56620817:1(58-65)Online publication date: 1-Jan-1997
A Fault-Tolerant Digital Artificial Neuron
Abstract
A simple fault-tolerant digital artificial neuron is introduced. Two digital implementations based on two different adders are examined. Reliability, fault coverage, and hardware redundancy analyses are carried out to characterize the proposed fault-tolerant digital neural module. These analyses reveal that, for a 114% increase in hardware, a 92.07% fault detection coverage and a 21.15% fault recovery coverage are attained for a four-input neural module.
References
[1]
1. T. Sejnowski, "Neural Network Learning Algorithms," Neural Computers , R. Eckmiller and C. Malsburg, eds., Springer-Verlag, Berlin, 1989, pp. 291-300.
[2]
2. K. Knight, "Connectionist Ideas and Algorithms," Comm. ACM, Vol. 33, No. 11, New York, Nov. 1990, pp. 59-74.
[3]
3. R. Hecht-Nielsen, Neurocomputing, Addison-Wesley, Reading, Mass., 1990.
[4]
1. W. Moore, "Conventional Fault Tolerance and Neural Computers," Neural Computers , R. Eckmiller and C. Malsburg, eds., Springer-Verlag, Berlin, 1989, pp. 29-37.
[5]
2. L. Belfore, B.W. Johnson, and J.H. Aylor, "The Design of Inherently Fault-Tolerant Systems," Concurrent Computations, S.K. Tewksbury et al., eds., Plenum Press, N.Y., 1988, pp. 565-583.
[6]
3. Q. Xu et al., "A Fault Tolerance Analysis of a Neocognitron Model," Proc. Int'l Joint Conf. Neural Networks, Vol. II, Washington, D.C., Jan. 1990, pp. II559-II562.
[7]
4. P. Franzon et al., "Defect Tolerant Implementations of Feed-Forward and Recurrent Neural Networks," Proc. IEEE Int'l Conf. Wafer Scale Integration, IEEE Computer Society Press, Los Alamitos, Calif, 1990, pp. 160-166.
[8]
5. M. Stevenson, R. Winter, and B. Widrow, "Sensitivity of Layered Neural Networks to Errors in the Weights," Proc. Int'l Joint Conf. Neural Networks, Vol. 1, Washington, D.C., Jan. 1990, pp. I337-I340.
[9]
1. J. Nijhuis et al., "Limits to the Fault Tolerance of a Feedforward Neural Network with Learning," Proc. 20th Int'l Symp. Fault-Tolerant Computing, New-Castle-Upon-Tyne, UK, June 1990, pp. 228-235.
[10]
2. L. Belfore, B.W. Johnson, and J.H. Aylor, "The Design of Inherently Fault-Tolerant Systems," in Concurrent Computations, S.K. Tewksbury et al., eds., Plenum Press, N.Y., 1988, pp. 565-583.
[11]
3. U. Ramacher and J. Beichter, "Architecture of a Systolic Neuro-Emulator," Proc. Int'l Joint Conf. Neural Networks, Vol. II, Washington, D.C., Jan. 1990, pp. II59- II63.
[12]
4. Y. Tohma, "Coding Techniques in Fault-Tolerant Self-Checking, and Fail-Safe Circuits," in Fault-Tolerant Computing, D.K. Pradhan, ed., Prentice Hall, Englewood Cliffs, NJ, 1986, pp. 336-411.
[13]
5. K. Hwang, Computer Arithmetic, J. Wiley & Sons, New York, 1979.
[14]
6. B.W. Johnson, Design and Analysis of Fault Tolerant Digital Systems, Addison-Wesley, Reading, Mass., 1989.
- A Fault-Tolerant Digital Artificial Neuron
Recommendations
A Multiple-Weight-and-Neuron-Fault Tolerant Digital Multilayer Neural Network
DFT '06: Proceedings of the 21st IEEE International Symposium on on Defect and Fault-Tolerance in VLSI SystemsThis paper introduces an implementation method of multiple weight as well as neuron fault-tolerant multilayer neural networks. Their fault-tolerance is derived from our extended back propagation learning algorithm called the deep learning method. The ...
Reliability Measure of Hardware Redundancy Fault-Tolerant Digital Systems with Intermittent Faults
While significant results are available which allow estimation of reliability measure for systems with permanent faults, no generally applicable results are available for intermittent (transient) faults. Methods are presented here which allow ...
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 ...
Comments
Information & Contributors
Information
Published In
Copyright © Copyright © 1993 IEEE. All Rights Reserved.
Publisher
IEEE Computer Society Press
Washington, DC, United States
Publication History
Published: 01 October 1993
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- View Citations1Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 12 Nov 2024
Other Metrics
Citations
Cited By
View all- Sibai FKulkarni S(1997)A Time-Multiplexed Reconfigurable NeuroprocessorIEEE Micro10.1109/40.56620817:1(58-65)Online publication date: 1-Jan-1997