Particle swarm optimization (PSO) motivated by the social behavior of organisms, is a step up to existing evolutionary algorithms for optimization of continuous nonlinear functions. Backpropagation (BP) is generally used for neural network training. Choosing a proper algorithm for training a neural network is very important. In this paper, a comparative study is made on the computational requirements of the PSO and BP as training algorithms for neural networks. Results are presented for a feedforward neural network learning a nonlinear function and these results show that the feedforward neural network weights converge faster with the PSO than with the BP algorithm.
G. K. Venayagamoorthy and V. G. Gudise, "Comparison of Particle Swarm Optimization and Backpropagation as Training Algorithms for Neural Networks," Proceedings of the 2003 IEEE Swarm Intelligence Symposium, 2003. SIS '03, Institute of Electrical and Electronics Engineers (IEEE), Jan 2003.
The definitive version is available at http://dx.doi.org/10.1109/SIS.2003.1202255
2003 IEEE Swarm Intelligence Symposium, 2003. SIS '03
Electrical and Computer Engineering
Keywords and Phrases
BP Algorithm; PSO; Backpropagation; Computational Requirements; Continuous Nonlinear Functions; Convergence; Convergence of Numerical Methods; Evolutionary Algorithms; Evolutionary Computation; Feedforward Neural Nets; Feedforward Neural Network; Neural Network Training; Nonlinear Functions; Optimisation; Particle Swarm Optimization
Article - Conference proceedings
© 2003 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.