Discrete time neural network synthesis using input activation functions

Abstract

A new possibility of synthesis of a new structure of neural networks (NN) is presented, where the following concepts are employed: (i) combination of input and output activation functions, (ii) input time-varying signal distribution, (iii) time-discrete domain synthesis and (iv) one-step learning iteration approach. The proposed NN synthesis procedures are useful for applications to identification and control of dynamical systems. The functionality of the proposed NN structure has been demonstrated with two numerical examples. >