Neural network technologies in system synthesis

Abstract

Abstract Work of artificial neural networks does not ensure the identification of order parameters (which are the principal diagnostic characters xi in biomedicine). We suggest to eliminate the 1st type uncertainties (when samplings xi statistically match for different physiological states of a human body) by introducing random setting of initial weight values wio of xi and subsequent multiple repetition (n≥1000) of artificial neural network settings. The xi ranking is made according to the weight samplings wi collected after such settings are applied.