Particle Swarm Optimization of Feed-Forward Neural Networks with Weight Decay

摘要

Training neural networks is a complex task of great importance in problems of supervised learning. In this work we analyze the use of the Particle Swarm Optimization algorithm and the cooperative variant with the weight decay mechanism for neural network training aiming better generalization performances. For evaluating these algorithms we apply them to benchmark classification problems of the medical field. The results showed that the weight decay mechanism implemented improved the mean generalization control of the two algorithms in all the tested problems.