BP neural network optimized with PSO algorithm and its application in forecasting

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.