Dynamic constructive fault tolerant algorithm for feedforward neural networks

IEICE Transactions on Information and Systems

Volumn E81-D, Issue 1, 1998, Pages 115-123

  Hammadi, Nait Charif ^a   Ohmameuda, Toshiaki ^a   Kaneko, Keiichi ^a   Ito, Hideo ^a  

^a CHIBA UNIVERSITY   (Japan)

Author keywords

DCFTA; Dynamic constructive algorithm; Fault tolerance; Feedforward neural network

Indexed keywords

ALGORITHMS; COMPUTER SIMULATION; FAULT TOLERANT COMPUTER SYSTEMS; LEARNING SYSTEMS;

DYNAMIC CONSTRUCTIVE FAULT TOLERANT ALGORITHMS (DCFTA);

FEEDFORWARD NEURAL NETWORKS;

EID: 0031703115     PISSN: 09168532     EISSN: None     Source Type: Journal    
DOI: None     Document Type: Article

References (18)

1. N.C. Hammadi and H. Ito, "Noise injection into hidden neurons: A learning technique for enhancing the performance of feedforward neural networks," Proc. Int. Conference on Neural Networks and Their Applications (NEURAP'97), pp.245-251, March 1997.
2. E.B. Bartlett, "Dynamic node architecture learning: An information theoretic approach," Neural Networks, vol.7, no.l, pp.129-140, 1994.
3. S.E. Fahlman and C. Lebier, "The cascade-correlation learning architecture," Advanced in Neural Information Processing Systems II, pp.524-532. 1989.
4. S.E. Fahlman and C. Lebier, "Recurrent Cascade-Correlation Architecture," Advanced in Neural Information Processing Systems III, Morgan Kaufman Publishers, pp.190-196. 1991.
5. E. Littman and H. Ritter, "Cascade network architectures," Proc. Int. Joint Conference On Neural Networks II, pp.398-404, 1992.
6. E. Littman and H. Ritter, "Cascade LLM Networks," in Artificial Neural Networks II, Elsevier Science Publishers, pp.253-257, 1992.
7. M.D. Emmerson and R.I. Damper, "Determining and improving the fault tolerance of multilayer perceptions in a pattern-recognition application," IEEE Trans. Neural Networks, vol.4, no.5, pp.788-793, 1993.
8. J. Nijhuis, B. Hofflinger, A. Schaik, and L. Spaanenburg, "Limits to fault-tolerance of a feedforward neural network with learning," Digest of Fault Tolerant Computing Symposium, pp.2~28-23~5, June 1990.
9. A.F Murray and P.J. Edwards, "Enhanced MLP performance and fault tolerance resulting from synaptic weight noise during training," IEEE Trans. Neural Networks, vol.5, no.5, pp.792-802, 1994.
10. D.S. Phatak and I. Koren, "Complete and partial fault tolerance of feedforward neural nets," IEEE Trans. Neural Networks, vol.6, no.2, pp.446-456, March 1995.
11. H. Ito and T. Yagi, "Fault tolerant design using error correcting code for multilayer neural networks," IEEE Int. Workshop on Defect and Fault Tolerance in VLSI systems, pp.177-184, 1994.
12. N.C. Hammadi and H. Ito, "A learning algorithm for fault tolerant feedforward neural networks," IEICE Trans. Inf. & Syst., vol.ESO-D, no.l, pp.21-27, Jan. 1997.
13. L.F.A. Wessels and E. Barnard , "Avoiding false local minima by proper initialization," IEEE Trans. Neural Networks, vol.3, no.6, pp.899-905, Nov. 1992.
14. N.C. Hammadi and H. Ito, "On the activation function and fault tolerance in feedforward neural networks," Proc. Int. Workshop on Dependability in Advanced Computing Paradigms, pp.29-34, June 1996.
15. Y. Tan and T. Nanya, "Fault-tolerant back-propagation model and its generalization ability," Digest IJCNN, pp.2516-2519, 1993.
16. G. Bolt, "Fault models for artificial neural networks," Digest IJCNN, pp.1373-1378, 1991.
17. N.S. Merchawi, S.T. Kumara, and C.R. Das, "A probabilistic model for the fault tolerance of multilayer perceptions," IEEE Trans. Neural Networks, vol.7, no. 1, pp.201-205, Jan. 1996.
18. N.C. Hammadi and H. Ito, "A learning algorithm for fault tolerant feedforward neural networks," IEICE Technical Report, FTS95-78, Feb. 1996.