Optimize neural network controller design using genetic algorithm
Ariel Kopel, Xiao-Hua Yu · 2008
The size of a neural network must be pre-determined before it can be trained for any application. Choosing the correct size of a neural network can increase its speed of response and thus improve the performance of the overall system. In this paper, a genetic algorithm is employed to find the optimal number of connections of a neural network controller which is used to regulate a class of DC power supplies. Satisfactory computer simulation results are obtained.