Title :
Quasi-efficient stochastic approximation on the basis of neural networks
Author :
Nazin, Alexander V.
Author_Institution :
Inst. of Control Sci., Moscow, Russia
Abstract :
A three-step recursive algorithm of a stochastic approximation type is proposed. The estimates are generated by the Polyak-Ruppert averaging technique with a neural network-based transformation of observations. The algorithm includes a procedure for neural network tuning to approximate the optimal transformation function. Theorems on convergence and asymptotic normality which demonstrate quasi-efficiency of the estimates are formulated
Keywords :
approximation theory; convergence of numerical methods; neural nets; Polyak-Ruppert averaging technique; asymptotic normality; convergence; neural network tuning; optimal transformation function; quasi-efficient stochastic approximation; Convergence; Neural networks; Noise generators; Noise measurement; Random variables; Recursive estimation; State estimation; Stochastic processes; Time measurement; Zinc;
Conference_Titel :
Decision and Control, 1994., Proceedings of the 33rd IEEE Conference on
Conference_Location :
Lake Buena Vista, FL
Print_ISBN :
0-7803-1968-0
DOI :
10.1109/CDC.1994.411076
