Structural Optimization of Neural Networks for Systems Modelling

Abstract

A new, optimal structure for backpropagation networks is proposed that enables modeling and on-line identification of dynamic systems. Usually, the activation function used for individual neurons is sigmoid-like, that enables modeling of nonlinear dynamic systems. However, because usually the required condition of uniformly distributed training examples is not satisfied, the backpropagation networks are not suitable for on-line training. To solve this problem and to neural network for modeling and on-line identification of real-time systems, the sigmoid functions have been modified, as described below, to be able specify the behavior of each neuron in a limited range of training data. In this way, the strong couplings among the network parameters are largely released and the training data for backpropagation networks need not to be chosen randomly from the identified input range. It is shown that the modified network exhibits a real-time memory capability and can be on-line trained.