Title :
Structure adaptation of polynomial stochastic neural nets using learning automata technique
Author :
Ramírez, E. Gòmez ; Poznyak, A.S.
Author_Institution :
Univ. La Salle, Mexico
Abstract :
The paper is concerned with the selection of a number of nodes in polynomial artificial neural nets containing stochastic noise perturbations in the outputs of each node. The suggested approach is based on a reinforcement learning technique. To solve this optimization problem we introduce a special performance index in such a way that the best number of nodes corresponds to the minimum point of the suggested criterion. This criterion presents a linear combination of a residual minimization functional and some “generalized variance” of the involved disturbances of random nature. A large value of the noise variance leads to a different optimal number of neurons in a neural network because of the “interference” effect. Simulation modeling results are presented to illustrate the effectiveness of the suggested approach
Keywords :
function approximation; learning (artificial intelligence); learning automata; minimisation; neural nets; noise; polynomials; stochastic automata; stochastic processes; generalized variance; learning automata technique; noise variance; performance index; polynomial stochastic neural nets; reinforcement learning technique; residual minimization functional; stochastic noise perturbations; structure adaptation; Artificial neural networks; Automatic control; Learning automata; Neural networks; Neurons; Pattern recognition; Performance analysis; Polynomials; Stochastic processes; Stochastic resonance;
Conference_Titel :
Neural Networks Proceedings, 1998. IEEE World Congress on Computational Intelligence. The 1998 IEEE International Joint Conference on
Conference_Location :
Anchorage, AK
Print_ISBN :
0-7803-4859-1
DOI :
10.1109/IJCNN.1998.682298
