Title :
A New Training Algorithm for RBF Neural Network Based on PSO and Simulation Study
Author :
Chun-tao, Man ; Kun, Wang ; Li-yong, Zhang
Author_Institution :
Sch. of Autom., Harbin Univ. of Sci. & Technol., Harbin, China
fDate :
March 31 2009-April 2 2009
Abstract :
Being difficult to determine hidden unitspsilas number and unsuitable to select central position in radial basis function (RBF) layer, particle swarm optimization and resource allocation (RAN) were proposed for training RBF neural networks. First, determine unitspsilas number in RBF layer using RAN. Then, optimize RBF parameters such as central position, width and weights based on PSO. The simulation results show that the new method has better approximation ability, the shorter time and the higher precision.
Keywords :
learning (artificial intelligence); particle swarm optimisation; radial basis function networks; resource allocation; PSO; RAN; RBF neural network; central position selection; neural network training; particle swarm optimisation; radial basis function; resource allocation; simulation study; Computational modeling; Computer science; Computer simulation; Feedforward systems; Function approximation; Neural networks; Particle swarm optimization; Radial basis function networks; Radio access networks; Transfer functions;
Conference_Titel :
Computer Science and Information Engineering, 2009 WRI World Congress on
Conference_Location :
Los Angeles, CA
Print_ISBN :
978-0-7695-3507-4
DOI :
10.1109/CSIE.2009.76
