Title :
Research on BP algorithm and PSO algorithm in the neural network
Author_Institution :
Autom. Eng. Coll., Qingdao Technol. Univ., Qingdao, China
Abstract :
Application of the basic BP algorithm, Levenberg-Marquardt algorithm and the PSO algorithm in the neural network are compared with each other. For the Iris and Breast Cancer data, the mean time of training, the minimum of training error, the minimum of test error, the mean recognition rate are compared. Characteristics of various algorithms for neural network training are analyzed in this paper, and simulation results show that, BP algorithm has some advantages in the limited time.
Keywords :
backpropagation; neural nets; particle swarm optimisation; BP algorithm; Levenberg-Marquardt algorithm; PSO algorithm; neural network; Artificial neural networks; Breast cancer; Feeds; IEEE Press; Particle swarm optimization; Training; BP Network; Levenberg-Marquardt; PSO Algorithm;
Conference_Titel :
Control Conference (CCC), 2010 29th Chinese
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-6263-6
