One approach to control of a neural network with variable signal conductivity

Abstract

The article focuses on a new extent to synthesize a control strategy of learning of a special artificial neural network with variable signal conductivity. The purpose of the research is to create new control strategy based on analysis of the neural network error signal. Also an approach to compute this control strategy is presented. The main result is contained in the necessity to realize the control strategy on the basis of preliminary training of the neural network with specific techniques. Also a crucial trajectory of the network’s error decreasing is given in the article. The trajectory may be computed using signal processing methods.