Adjusting Weights and Architecture of Neural Networks through PSO with Time-Varying Parameters and Early Stopping

• Published in: 2008 10th Brazilian Symposium on Neural Networks Vol. 10; pp. 33 - 38
• Main Authors: Teixeira, L.A., Oliveira, F.T.G., Oliveira, A.L.I., Filho, C.
• Format: Conference Proceeding Journal Article
• Language: English
• Published: IEEE 01-10-2008
• Subjects: Architecture Selection; Artificial neural network; Automatic generation control; Backpropagation algorithms; Computational efficiency; Computer architecture; Computer networks; Neural networks; Particle swarm optimization; Space exploration; Time varying systems; Topology
• ISBN: 9781424432196; 1424432197
• ISSN: 1522-4899; 2375-0235
• DOI: 10.1109/SBRN.2008.18

This paper presents results of an approach to optimize architecture and weights of MLP Neural Networks, which is based on particle swarm optimization with time-varying parameters and early stopping criteria. This approach was shown to achieve a good generalization control, as well as similar or better results than other techniques, but with a lower computational cost, with the ability to generate small networks and with the advantage of the automated architecture selection, which simplify the training process.