Genetic Algorithm for Optimization of Neural Network Structure and Weight Distribution
ZHOU Shi-guan, LI Zhong-xia (College of Electromechanical Engineering, Southern Institute of Metallurgy, Ganzhou 341000, China)
Simultaneity optimization for structure and weight distribution of neural network belongs to two class evolutionary method. First step, neural network structure is evolved; second step, neural network weight distribution is evolved, and use different code mode and fitness function in process of two class evolutionary, and modified genetic algorithm---reverse mutation operation was used. Reverse mutation operation can search according to the expectant direction, and do not bring premature convergence. Emulation result shows expectant optimization efficiency is obtained with genetic algorithm.
【CateGory Index】： TP183