The Research on BP Neural Network Model Based on Guaranteed Convergence Particle Swarm Optimization
Authors:
- Pingzhou TangPTPingzhou Tang
- Zhaocai XiZXZhaocai Xi
- 1 December 2008
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 13-16
Abstract
In applying neural network to identification, back propagation (BP) algorithm is usually trapped to a local optimum and has a low speed of convergence, whereas particle swarm optimization (PSO) is advantageous in terms of global optimal searching. In this paper, a new algorithms which combines guaranteed convergence particle swarm optimizer (GCPSO) algorithm with BP (Back Propagation) algorithm is introduced in this paper and applied to BP neural networks to optimize the parameters of BP neural networks so as to improve the convergence speed and precision of BP neural networks. Compared with the BP algorithm and PSO-BP algorithm, the results of the simulation show that the algorithm of BP Neural Network Model Based on Guaranteed Convergence Particle Swarm Optimization speeds up the convergence process and enhances the accurate rate in pattern recognition.Keywords
This publication has 3 references indexed in Scilit:
- Evolving neural nets for fault diagnosis of power transformersIEEE Transactions on Power Delivery, 2003
- A Robust Evolutionary Algorithm for Training Neural NetworksNeural Computing and Applications, 2001
- Improved operation of power transformer protection using artificial neural networkIEEE Transactions on Power Delivery, 1997