Title :
A new learning algorithm for RBF neural networks
Author :
Man Chun-tao ; Yang Xu ; Zhang Li-yong
Author_Institution :
Sch. of Autom., Harbin Univ. of Sci. & Technol., Harbin
Abstract :
A new method is presented in order to solve the problem of randomness of the initial selection for nearest neighbor clustering algorithm and redundant nodes introduced by subtractive clustering algorithm, namely, the algorithm that contain pruning technique of subtractive clustering algorithm and nearest neighbor clustering algorithm combine together,and accomplish the learning of training samples. The simulation results show that the effectiveness of the new algorithm.
Keywords :
learning (artificial intelligence); pattern clustering; radial basis function networks; RBF neural networks; learning algorithm; nearest neighbor clustering algorithm; pruning technique; subtractive clustering algorithm; Approximation algorithms; Attenuation; Clustering algorithms; Convergence; Feedforward neural networks; Function approximation; Nearest neighbor searches; Neural networks; Radial basis function networks; Training data; Nearest Neighbor Clustering Algorithm; Pruning Technique; RBF Neural Network; Subtractive Clustering Algorithm;
Conference_Titel :
Systems and Control in Aerospace and Astronautics, 2008. ISSCAA 2008. 2nd International Symposium on
Conference_Location :
Shenzhen
Print_ISBN :
978-1-4244-3908-9
Electronic_ISBN :
978-1-4244-2386-6
DOI :
10.1109/ISSCAA.2008.4776251
