Research on Structure Dynamic Neural Network

摘要

A model of structure dynamic neural network,which is simulates the learning skills such as human beings and animals,is presented.This model contains two main steps: 1) The structure learning phase possesses the ability of online generation and ensures the number of the neural nodes of the neural network; 2) The parameter learning phase adjusts the interconnection weights of neural network to achieve favourable approximation performance.The structure learning algorithm consists of growing and pruning methods,and then the Lyapunov stability theory is used to analyze the stability of this algorithm.Finally,we use this new neural network to track the nonlinear functions,simulation results show that this new algorithm can achieve favourable performance.