Solution to China’s GDP Prediction Problem by BP Neural Network
Because the choice and important of learning rate , the higher of η and the faster convergence it will be, but it may cause instability or function vibration if is too high; if is lower, although it may avoid instability, the speed of function convergence will reduce. In order to solve the contradiction, we introduce a variable of , and if the this time is the same as that of the previous time, the weighted summation value will increase and it results in the regulation speed of right value at the stable regulation; and if the this time is contrary to that of the previous time, it indicates that a certain vibration and now the result of summation will make the value of decrease to play a role in stability and increase the speed of function convergence.
Shaobo Zhong, Yimin Cheng and Xilong Qu
J. Li et al., "Solution to China’s GDP Prediction Problem by BP Neural Network", Applied Mechanics and Materials, Vols. 50-51, pp. 423-427, 2011