Neural networks synthesis based on stochastic approximation algorithm
暂无分享,去创建一个
A new method for neural networks synthesis is presented. This is an algorithm of the stochastic approximation type, which is designed to optimize functions with non-unique stationary points. This method differs from the usual backpropagation algorithm which cannot deal with the optimization of multimodal functions. The stochastic approximation method presented in this study consists of the Kiefer-Wolfowitz procedure. Numerical experiments related to a phosphate calcinator modelling are presented in order to illustrate the performance of the optimization algorithm associated with neural networks synthesis
[1] James A. Anderson,et al. Neurocomputing: Foundations of Research , 1988 .
[2] H. Kushner. Stochastic approximation algorithms for the local optimization of functions with nonunique stationary points , 1972 .
[3] J. Kiefer,et al. Stochastic Estimation of the Maximum of a Regression Function , 1952 .
[4] M. Haloua,et al. GENERALIZED PREDICTIVE CONTROL OF AN INDUSTRIAL CALCINATION REACTOR , 1992 .