On the activation function and fault tolerance in feedforward neural networks

IEICE Transactions on Information and Systems

Volumn E81-D, Issue 1, 1998, Pages 66-72

  Hammadi, Nait Charif ^a   Itq, Hideo ^a  

^a CHIBA UNIVERSITY   (Japan)

Author keywords

Critical weights; Fault tolerance; Feedforward neural network; Generalization ability; Xor problem

Indexed keywords

COMPUTER SIMULATION; FAULT TOLERANT COMPUTER SYSTEMS; FORMAL LOGIC;

ACTIVATION FUNCTIONS;

FEEDFORWARD NEURAL NETWORKS;

EID: 0031681567     PISSN: 09168532     EISSN: None     Source Type: Journal    
DOI: None     Document Type: Article

References (19)

1. S. Hayken, Neural Networks, A comprehensive foundation, IEEE Press, 1994.
2. R.C. Frye, E.A. Rietman, and C.C. Wong, Backpropagation learning and nonidealities in analog neural network hardware, IEEE Trans. Neural Networks, vol.2, no.1. pp.110-117, Jan. 1991.
3. 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.228-235, June 1990.
4. B.E. Segee and M.J. Carter, Fault tolerance of pruned multilayer networks, Digest of Int. Joint Conf. Neural Networks, July 1991.
5. J.I. Minnix, Fault tolerance of backpropagation neural network trained on noisy inputs, Digest of Int. Joint Conf. Neural Networks, June 1992.
6. A.F. Muroay and P.J. Edwards, Enhanced MLP perfor-mance and fault tolerance resulting from synaptic weight noise during training, IEEE Trans. Neural Networks, vol.5, no.5, pp.792-802, 1994.
7. M.D. Emmerson and R.I. Damper, Determining and improving the fault tolerance of multi layer perception in a pattern-recognition application, IEEE Trans. Neural Networks, vol.4, no.5, pp.788-793, 1993.
8. Y. Tan and T. Nanya, Fault-tolerant back-propagation model and its generalization ability, Digest of Int. Joint Conf. Neural Networks, 1993.
9. O.P. Drago and S. Ridella, Statistically controlled activation weight initialization (SCAWI), IEEE Trans. Neural Networks, vol.3, no.4, pp.627-631, July 1992.
10. R. Reed, Pruning algorithms -A survey, IEEE Trans. Neural Networks, vol.4, no.5, pp.740-747, Sept. 1993.
11. S.B. Holden and P.J.W. Rayner, Generalization and PAC learning: Some new results for the class of generalized single-layer networks, IEEE Trans. Neural Networks, vol.6, no.2, pp.468-480, March 1995.
12. J.S.N. Jean and J. Wang, Weight smoothing to improve network generalization, IEEE Trans. Neural Networks, vol.5, no.5, pp.468-480, Sept. 1995.
13. G. Bolt, Fault models for artificial neural networks, Digest of Int. Joint Conf. Neural Networks, pp.1373-1378, 1991.
14. 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.
15. E.D. Karnon, A simple procedure for pruning backpropagation trained neural networks, IEEE Trans. Neural Networks, vol.1, no.2, pp.239-242, June 1995.
16. X.-H. Yu, G.-A. Chen, and S.-X. Cheng, Dynamic learning rate optimization of the backpropagation algorithm, IEEE Trans. Neural Networks, vol.6, no.3, pp.669-677, May 1995.
17. N.S. Merchawi, S.T. Kumara, and C.R. Das, A probabilistic model for the fault tolerance of multilayer perceptrons, IEEE Trans. Neural Networks, vol.7, no.I, pp.201-205, Jan. 1996.
18. L.P.J. Veelenturf, Analysis and Applications of Artificial Neural Networks, Prentice Hall International (UK) Ltd., 1995.
19. J. Cao and A. Cichocki, Adaptive multilayer perceptron with automatic gain scaling, IEICE Technical Report, NC96-117, June 1996.