Title :
BP neural network optimized with PSO algorithm and its application in forecasting
Author :
Guo, Wen ; Qiao, Yizheng ; Hou, Haiyan
Author_Institution :
Sch. of Control Sci. & Eng., Shandong Univ., Jinan
Abstract :
An approach that neural network optimized with PSO algorithm is proposed in the paper. Unlike conventional training method with gradient descent method only, this paper introduces a hybrid training algorithm by combining the PSO and BP algorithm. The PSO is used to optimize the initial parameters of the BP neural network, including the weights and biases. It can effectively better the cases that network is easily trapped to a local optimum and has a slow velocity of convergence. The experiment results show the method in the paper above conventional one has greater improvement in both accuracy and velocity of convergence for BP neural network.
Keywords :
backpropagation; neural nets; particle swarm optimisation; road traffic; BP neural network training algorithm; PSO algorithm; gradient descent method; traffic flow forecasting application; Artificial neural networks; Computer networks; Convergence; Machine learning; Machine learning algorithms; Neural networks; Particle swarm optimization; Pattern classification; Telecommunication traffic; Testing; BP Neural Network; Evolution Computation; Forecasting; Particle Swarm Optimization; training algorithm;
Conference_Titel :
Information Acquisition, 2006 IEEE International Conference on
Conference_Location :
Shandong
Print_ISBN :
1-4244-0528-9
Electronic_ISBN :
1-4244-0529-7
DOI :
10.1109/ICIA.2006.305796
