A real-valued genetic algorithm is proposed to the optimization problem with continuous variables. It is composed of a simple and general-purpose dynamic scaled fitness and selection operator, real-valued crossover operator, mutation operators and adaptive probabilities for these operators. The proposed algorithm is tested by two generally used functions and is applied to the training of a neural network for image recognition. Experimental results show that the proposed algorithm is an efficient global optimization algorithm.
A new evolutionary computation method
1997-01-01
393387 byte
Conference paper
Electronic Resource
English
An New Evolutionary Computation Method
British Library Conference Proceedings | 1997
|Intelligent Path Planning With Evolutionary Computation
British Library Conference Proceedings | 2010
|Architecture for high-speed evolutionary computation
Online Contents | 2004
|Evolutionary computation technologies for space systems
Tema Archive | 2005
|3D airspace design by evolutionary computation
IEEE | 2008
|