Simple item record

Please use this identifier to cite or link to this item: http://hdl.handle.net/10203/8904

Hit : 109   Download : 0

Metadata Downloads : or

Title	Training Neural Network Controller Using Modified Genetic Algorithm
Authors	Jeong, Il-Kwon; Lee, Ju-Jang
Issue Date	1995
Publisher	The Korean Institute of Electrical Engineers
	대한전기학회
Citation	제어계측연구회 합동학술발표회 pp.149-154
Abstract	We propose a modified genetic algorithm(MGA) and show application of the genetic algorithm to control systems including neural networks. Genetic algorithms are getting more popular nowadays because of their simplicity and robustness. Genetic algorithms are global search techniques for optimization and many other problems. A feed-forward neural network which is widely used in control applications usually learns by error back propagation algorithm(EBP). But, when there exist certain constraints, EBP cannot be applied. We apply a genetic algorithm to such a case using real value coding method. To improve hil-claimbing capability and speed up the convergence, we propose a modified genetic algorithm(MGA). The validity and efficiency of the proposed algorithm, MGA are shown by some simulation examples of system identification and nonlinear system control including cart-pole systems and robot manipulators.
URI	http://hdl.handle.net/10203/8904
Link	http://www.kiee.or.kr/
Appears in Collections	EE-Conference Papers(학술회의논문)

There are no files associated with this item.

FusionCharts.

Items in KOASAS are protected by copyright, with all rights reserved, unless otherwise indicated.