Title :
An Improved RBF Neural Network Based on Evolutionary Programming
Author :
Zhang Lin ; Dang Xuanju ; Zeng Silin
Author_Institution :
Sch. of Comput. & Control, Guilin Univ. of Electron. Technol., Guilin, China
Abstract :
For the problem of local minimum for gradient descent method used to train an RBF (radial basis function) neural network, EP (evolutionary programming) is introduced to the training of RBF neural network in this paper. The combination method of EP and gradient descent method can effectively avoid local minimum, and provides a more reasonable network design. The effectiveness of the proposed scheme is demonstrated by the simulation of a nonlinear system control.
Keywords :
evolutionary computation; gradient methods; radial basis function networks; RBF neural network; evolutionary programming; gradient descent method; local minimum; nonlinear system control; radial basis function neural network; Computer architecture; Computer networks; Feedforward neural networks; Functional programming; Genetic programming; Integrated circuit technology; Neural networks; Nonlinear systems; Process design; Vectors; evolutionary programming; gradient descent method; local minimum; radial basis function;
Conference_Titel :
Genetic and Evolutionary Computing, 2009. WGEC '09. 3rd International Conference on
Conference_Location :
Guilin
Print_ISBN :
978-0-7695-3899-0
DOI :
10.1109/WGEC.2009.80
