The best pattern recognizers in most instances are human, yet we do not understand how human recognize patterns. The pattern recognition is critical in the human decision task, the more relevant the pattern at your disposal, the better your decision will be. More recently, neural network techniques in pattern recognition have been receiving increasing attention. The design of a recognition system requires careful attention to the following issues: definition of pattern classes, sensing environment, pattern representation, feature extraction and selection, learning, selection of training and test samples. A review of fault tolerance in neural networks is presented. Work relating to the various issues of reliability, complexity and capacity are considered, as well as covering both empirical results and a general treatment of theoretical work. It is shown that in the majority of the work, few sound theoretical methods to be applied and that conventional fault tolerance techniques cannot straightforwardly be transferred to neural networks. It is often concluded that all the neural networks are often cited as being fault tolerant. To support this work a fundamental prerequisite is described which can act as base for research into the fault tolerance of neural networks. (The performance analysis of fault tolerance is done using uniform and Gaussian distribution. )

1. Zhi-Hua Zhou Shi-Fu Chen Zhao-Qian Chen (2001) "Improving Tolerance of Neural Networks against Multi-Node Open Fault" Proceedings of the INNS-IEEE International Joint Conference on Neural Networks, Washington, DC, 2001, vol. 3, pp. 1687-1692.
2. MargaritaSordo Sanchez " A Neurosymbolic Approach to the Classification of Scarce and Complex Data" Advanced Computation Laboratory Imperial Cancer Research Fund 61 Lincoln's Inn Fields, London WC2A 3PX, England.
3. David A Medler and Michael R W Dawson "Using Redundancy to Improve the Performance of Artificial Neural Networks" Biological Computation Project, Dept of Psychology , University of Alberta , Canada.
4. Dhananjay S Pathak" Fault Tolerance Artificial Neural Network" Electrical Engg dept, State University of New York, Binghamton, NY.
5. Dhananjay S Pathak, Elko Tchernev" Synthesis of Fault Tolerance Neural Network" Dept of Computer Science Engg, University of Maryland County, Baltimore.
6. P. J. Edwards and A. F. Murray, "Fault Tolerance via Weight Noise in Analog VLSIImplementations of MLP's – A Case study with EPSILON," IEEE Transaction on Circuits andSystems-II: Analog and Digital Signal Processing, vol. 45, no. 9, September 1998.
7. N. C. Hammadi and H. Ito, "A Learning Algorithm for Fault Tolerant FeedforwardNeuralNetworks," IEICE Trans. Information and Systems, vol. E80-D, no. 1, pp. 21-27, 1997. Applications, vol. 42, no. 6, June 1995
8. . C. T. Chiu, K. Mehrotra, C. K. Mohan, and S. Ranka,, "TrainingTechniques to obtain faulttolerantneural network," 24th International Symposium on Fault-Tolerant Computing, pp360-369, June 1994.
9. G. Bolt, "Investigating Fault Tolerance in Artificial Neural Networks," University of York, Department of Computer Science, Technical Report YCS 154, Heslington, York, England, 1991.
10. V. Cherkassky, "Comparison of Adaptive methods for function estimation from samples," IEEE Transaction on Neural Networks, vol. 7, no. 4, July 1996.

Feedforward Neural Networks Fault Tolerance Fault Model Graceful Degradation Pattern Recognition