Learning algorithms which make multilayer neural networks multiple-weight-and-neuron-fault tolerant

IEICE Transactions on Information and Systems

Volumn E91-D, Issue 4, 2008, Pages 1168-1175

  Horita, Tadayoshi ^a   Takanami, Itsuo ^b   Mori, Masatoshi ^a  

^a POLYTECHNIC UNIVERSITY   (Japan)

^b NONE

Author keywords

Fault tolerance; Multilayer neural network; Multiple fault; Neuron fault; Weight fault

Indexed keywords

FAULT TOLERANCE; LEARNING ALGORITHMS; MULTILAYERS; NEURAL NETWORKS; NEURONS;

ANALYTICAL RESULTS; LEARNING METHODS; LEARNING PHASE; MULTIPLE FAULTS; NEURON FAULTS; OUTPUT ERRORS; OUTPUT FAULTS; WEIGHT FAULTS;

MULTILAYER NEURAL NETWORKS;

EID: 65949122408     PISSN: 09168532     EISSN: 17451361     Source Type: Journal    
DOI: 10.1093/ietisy/e91-d.4.1168     Document Type: Article

References (16)

1. D.S. Phatak and I. Koren, "Complete and partial fault tolerance of feedforward neural nets," IEEE Trans. Neural Netw., vol.6, no.2, pp.446-456, 1995.
2. S.E. Fahlman, et al., "Neural nets learning algorithms and benchmarks database," maintained by S.E. Fahlman et al. at the Computer Science Dept., Carnegie Mellon University.
3. J. Nijhuis, B. Hoefflinger, A. van Schaik, and L. Spaanenburg, "Limits to the fault-tolerance of a feedforward neural network with learning," FTCS, pp.228-235, 1990.
4. Y. Tan and T. Nanya, "A faut-tolerant multi-layer neural network model and its properties," IEICE Trans. Inf. & Syst. (Japanese Edition), vol.J76-D-I, no.7, pp.380-389, July 1993.
5. R.D. Clay and C.H. Séquin, "Fault tolerance training improves generalization and robustness," Int'l. Joint Conf. on Neural Networks, pp.I-769-774, 1992.
6. T. Ito and I. Takanami, "On fault injection approaches for fault tolerance of feedforward neural networks," Sixth Asian Test Symposium at Akita, pp.88-93, 1997.
7. N.C. Hammadi and H. Ito, "A learning algorithm for fault tolerant feedforward neural networks," IEICE Trans. Inf. & Syst., vol.E80-D, no.1, pp.21-26, Jan. 1997.
8. N.C. Hammadi, T. Ohmameuda, K. Kaneko, and H. Ito, "Fault tolerant constructive algorithm for feedforward neural networks," PRFT'97, pp.215-220, 1997.
9. N.C. Hammadi, T. Ohmameuda, K. Kaneko, and H. Ito, "Dynamic constructive fault tolerant algorithm for feedforward neural networks," IEICE Trans. Inf. & Syst., vol.E81-D, no.1, pp.115-123, Jan. 1998.
10. S. Cavalieri and O. Mirabella, "A novel learning algorithm which impoves the partial fault tolerance of multilayer neural networks," Neural Networks (Pergamon), vol.12, no.1, pp.91-106, 1999.
11. N. Kamiura, Y. Hata, and N. Matsui, "Fault tolerant feedforward neural networks with learning algorithm based on synaptic weight limit," Proc. 5th IEEE International On-Line Testing Workshop, pp.222-226, Rhodes, 1999.
12. N. Kamiura, Y. Taniguchi, Y. Hata, and N.Matsui, "A learning algorithm with activation function manipulation for fault tolerant neural networks," IEICE Trans. Inf. & Syst., vol.E84-D, no.7, pp.899-905, July 2001.
13. H. Takase, H. Kita, and T. Hayashi, "Weight minimization approach for fault tolerant multi-layer neural networks," Proc. Int'l Journal Conference on Neural Networks, pp.2656-2660, 2001.
14. I. Takanami and Y. Oyama, "A novel learning algorithm which makes multilayer neural networks multiple-weight-fault tolerant," IEICE Trans. Inf. & Syst., vol.E86-D, no.12, pp.2536-2543, Dec. 2003.
15. T. Horita and I. Takanami, "Novel learning algorithms which make multilayer neural networks multiple-weight-and-neuron-fault tolerant," Proc. ICONIP 2005, pp.564-569, 2005.
16. M. Matsumoto and T. Nishimura, "Mersenne twister: A 623-dimensionally equidistributed uniform pseudo-random number generator," ACM Trans. Model. Comput. Simul., vol.8, no.1, pp.3-30, 1998.