Finding Optimal Neural Network Architecture Using Genetic Algorithms

Abstract. This work deals with methods for finding optimal neural network architectures to learn particular problems. A genetic algorithm is used to discover suitable domain specific architectures; this evolutionary algorithm applies direct codification and uses the error from the trained network as a performance measure to guide the evolution. The network training is accomplished by the back-propagation algorithm; techniques such as training repetition, early stopping and complex regulation are employed to improve the evolutionary process results. The evaluation criteria are based on learning skills and classification accuracy of generated architectures 1