Performance Improvement of RBF Network Using ART2 Algorithm and Fuzzy Logic System

This paper proposes an enhanced RBF network that enhances learning algorithms between input layer and middle layer and between middle layer and output layer individually for improving the efficiency of learning The proposed network applies ART2 network as the learning structure between input layer and middle layer And the auto-tuning method of learning rate and momentum is proposed and applied to learning between middle layer and output layer, which arbitrates learning rate and momentum dynamically by using the fuzzy control system for the arbitration of the connected weight between middle layer and output layer The experiment for the classification of number patterns extracted from the citizen registration card shows that compared with conventional networks such as delta-bar-delta algorithm and the ART2-based RBF network, the proposed method achieves the improvement of performance in terms of learning speed and convergence.

[1]  James Ting-Ho Lo,et al.  Multilayer perceptrons and radial basis functions are universal robust approximators , 1998, 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227).

[2]  Si-Woong Jang,et al.  Recognition of Car License Plate by Using Dynamical Thresholding Method and Enhanced Neural Networks , 2003, CAIP.

[3]  No Value,et al.  Proceedings of IJCNN'98 , 1998 .

[4]  Robert A. Jacobs,et al.  Increased rates of convergence through learning rate adaptation , 1987, Neural Networks.

[5]  Marimuthu Palaniswami,et al.  Effects of moving the centers in an RBF network , 1998, 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227).

[6]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .