Penalty terms for fault tolerance

IEEE International Conference on Neural Networks - Conference Proceedings

Volumn 2, Issue , 1997, Pages 943-947

  Edwards, P J ^a   Murray, A F ^a  

^a UNIVERSITY OF EDINBURGH   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

DISTRIBUTED COMPUTATIONS; FAULT MODEL; HARDWARE ERROR; PENALTY TERM; REAL-WORLD TASK; REALISTIC MODEL; ROUGHNESS PENALTY; SOLUTION LOCUS;

NEURAL NETWORKS; OPTIMIZATION; COMPUTER HARDWARE; ERROR ANALYSIS; FAULT TOLERANT COMPUTER SYSTEMS; LEARNING ALGORITHMS; LEARNING SYSTEMS;

FAULT TOLERANCE; NEURAL NETWORKS;

PENALTY TERMS;

EID: 0030702546     PISSN: 10987576     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICNN.1997.616152     Document Type: Conference Paper

References (14)

1. C. Bishop. Curvature-driven smoothing in backpropagation neural networks. In Proc. International Joint Conference on Neural Networks, volume 2, pages 749-752,1990.
2. C. Bishop. Training with noise is equivalent to Tikhonov regularization. Neural Computation, 7(1):108-116,1995.
3. M. Carter. The 'illusion' of fault tolerance in neural networks for pattern recognition and signal processing. In Proc. Technical Session on Fault-Tolerant Integrated Systems, University of New Hampshire, Durham NH, 1988.
4. P. Edwards and A. Murray. Can deterministic penalty terms model the effects of synaptic weight noise on network fault-tolerance? International Journal of Neural Systems, 6(4):401-416,1995.
5. P. Edwards and A. Murray. Analogue Imprecision in MLP Training. World Scientific, August 1996.
6. P. Edwards and A. Murray. Modelling weight-and input-noise in MLP learning. In Proc. International Conference on Neural Networks, volume 1, pages 78-83, Washington D.C., June 1996.
7. P. Edwards and A. Murray. Fault-tolerance via weight-noise in analogue VLSI implementations-A case study with EP-SILON. IEEE Proceedings on Circuits and Systems II: Analog and Digital Signal Processing, 1997. Submitted for publication.
8. T. Lehmann. Hardware learning in analogue VLSI neural networks. PhD thesis, Technical University of Denmark, 1994.
9. A. Murray and P. Edwards. Synaptic weight noise during MLP training: Enhanced MLP performance and fault tolerance resulting from synaptic weight noise during training. IEEE Trans. Neural Networks, 5(5):792-802, Sept. 1994.
10. C. Neti, M. Schneider, and E. Young. Maximally fault tolerant neural networks. IEEE Trans. Neural Networks, 3(1): 14-23, 1992.
11. E. Nordstrom, O. Gallmo, L. Asplund, M. Gustafsson, and B. Eriksson. Neural networks for admission control in an ATM network. In L. Niklasson and M. Boden, editors, Con-nectionism in a Broad Perspective: Selected papers from the Swedish Conference on Connectionism-1992, pages 239-250. Ellis Horwood, 1992.
12. D. Ruck, S. Rogers, M. Kabrisky, M. Oxley, and B. Suter. The multilayer perceptron as an approximation to a bayes optimal disciminant function. IEEE Trans. Neural Networks, l(4):296-298,1990.
13. G. Seber and C. Wild. Nonlinear Regression. Wiley, NY, 1989.
14. C. Sequin and R. Clay. Fault tolerance in artificial neural networks. In Proc. International Joint Conferenceon Neural Networks, volume 1, pages 703-708, San Diego, 1990.