Multilayer feedforward networks are universal approximators
Neural Networks
Reliable classification using neural networks: a genetic algorithm and backpropagation comparison
Decision Support Systems
Swarm intelligence
Parameter Selection in Particle Swarm Optimization
EP '98 Proceedings of the 7th International Conference on Evolutionary Programming VII
Hi-index | 0.00 |
Given the relative limitations of BP and GA based leaning algorithms, Particle Swarm Optimization (PSO) is proposed to train Artificial Neural Networks (ANN) for the diagnosis of unexplained syncope. Compared with BP and GA based training techniques, PSO based learning method improves the diagnosis accuracy and speeds up the convergence process. Experimental results show that PSO is a robust training algorithm and should be extended to other real-world pattern classification applications.