Using genetic programming for artificial neural network development and simplification
Daniel Rivero, Julián Dorado, Juan R. Rabuñal, Alejandro Pazos · Computational intelligence · 2006
The creation process of Artificial Neural Networks (ANNs) used to be quite slow and the human expert had to test several architectures until finding the one that achieves the best results for the solution of a certain problem. This work presents a new technique that uses Genetic Programming (GP) for automatically creating ANNs. This technique also allows the obtaining of simplified networks with few neurons for solving the problem. In order to measure the performance of the system and to compare the results with other ANN generation and training methods with Evolutionary Computation (EC) techniques, several tests were performed with problems based on some of the most used test databases. The results of those comparisons showed that the system achieved good results comparable with already existing techniques and, in most of the cases, they worked better than those techniques.