EDUARDO GÓMEZ-RAMÍREZFAlexander S. Poznyak2026-03-222026-03-22199810.1080/00207729808929506https://doi.org/10.1080/00207729808929506https://andeanlibrary.org/handle/123456789/62779Abstract The selection of a number of nodes in artificial neural nets containing stochastic noise perturbations in the outputs and inputs of each node is examined. 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 networks because of the ‘interference’ effect. The optimal point is obtained by the learning procedure based on the Bush-Mosteller reinforcement scheme. This numerical method is commonly used in Intelligent Control Theory. Simulation modelling results are presented to illustrate the effectiveness of the suggested approachenAdaptation (eye)AutomatonArtificial neural networkComputer scienceLearning automataArtificial intelligenceNeural adaptationTheoretical computer sciencearticle