Prediction capability of neural networks trained by Monte-Carlo paradigm

The Monte-Carlo training paradigm for Artificial Neural Networks has been studkd, the training short cut to reduce the training time has been discussed, and the prediction capability of such a trained neural network has been compared with the prediction capability of a neural net trained by the Backpropagation paradigm and with the statistical approach of the Diserimintmt Analysis. The Artificial Neural Network trained by the Monte-Carlo method proves itself as a reliable prediction tool which is superior to Discriminartt Analysis and the BackPropagation training paradigm.

[1]  Anders Krogh,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[2]  R. R. Hashemi,et al.  A backpropagation neural network for risk assessment , 1993, Proceedings of Phoenix Conference on Computers and Communications.

[3]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[4]  Geoffrey E. Hinton,et al.  Learning and relearning in Boltzmann machines , 1986 .

[5]  Shiro Usui,et al.  Neural Computing , 1989, IFIP Congress.

[6]  Ray R. Hashemi,et al.  Conflict resolution in inductive learning from examples , 1992, SAC '92.

[7]  M Barinaga.  Neuroscience models the brain. , 1990, Science.

[8]  F R Jelovsek,et al.  Developmental toxicity risk assessment: a rough sets approach. , 1993, Methods of information in medicine.

[9]  Philip D. Wasserman,et al.  Neural computing - theory and practice , 1989 .