An empirical study of non-binary genetic algorithm-based neural approaches for classification
Parag C. Pendharkar, James Allen Rodger · 1999
In this paper, we describe a genetic algorithm (GA) based approach for learning connection weights for an artificial neural network (ANN). We use simulated data sets to compare the GA based approach for learning connection weights against the traditional back-propagation algorithm. Our results indicate that GA based training of ANN has a higher reliability (in terms of over-fitting the training data set) and predictive power than the traditional back-propagation algorithm.