Title: Research on structure dynamic neural networks

Authors: Hong-gui Han, Jun-fei Qiao, Xin-yuan Li

Addresses: College of Electronic and Control Engineering, Beijing University of Technology, Chaoyang, Beijing 100124, China. ' College of Electronic and Control Engineering, Beijing University of Technology, Chaoyang, Beijing 100124, China. ' College of Electronic and Control Engineering, Beijing University of Technology, Chaoyang, Beijing 100124, China

Abstract: A model of structure dynamic neural network, which simulates the learning skills such as human beings and animals, is proposed in this paper. 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 analyse the stability of this new algorithm. Finally, this new dynamic neural network is used to track the non-linear functions; simulation results show that this new algorithm can achieve favourable performance.

Keywords: neural network structure; dynamic structures; growing methods; pruning methods; modelling; structure learning; parameter learning; simulation.

DOI: 10.1504/IJMIC.2010.032373

International Journal of Modelling, Identification and Control, 2010 Vol.9 No.1/2, pp.152 - 160

Available online: 01 Apr 2010

Full-text access for editors Access for subscribers Purchase this article Comment on this article