Multilayer feedforward networks are universal approximators
Neural Networks
Neural Networks: A Comprehensive Foundation
Neural Networks: A Comprehensive Foundation
Using the particle swarm optimization technique to train a recurrent neural model
ICTAI '97 Proceedings of the 9th International Conference on Tools with Artificial Intelligence
Fuzzy Adaptive Turbulent Particle Swarm Optimization
HIS '05 Proceedings of the Fifth International Conference on Hybrid Intelligent Systems
Expert Systems with Applications: An International Journal
Hi-index | 0.00 |
Multilayer perceptron networks have been successfully trai- ned by error backpropagation algorithm. We show that Particle Swarm Optimization(PSO) with minimum velocity constraints can efficiently be applied to train multilayer perceptrons to overcome premature convergence and alleviates the influence of dimensionality increasing. The experiments of two multilayer perceptrons trained by PSO with minimum velocity constraints are carried out. The result clearly demonstrate the improvement of the proposed algorithm over the standard PSO in terms of convergence.