A New Layer by Layer Training Algoithm for Multilajer Feedforward Neural Networks

摘要：

A New Layer by Layer (NLBL) training algorithm for speeding up the training of multilayer feedforward neural networks is presented in this paper. It uses an approach similar to that of the Layer by Layer (LBL) algorithm, taking into account the input errors of the output layer and hidden layer. The proposed NLBL algorithm, however, is not burdened by the need to calculatethegradientoftheerrorfunction. Furthermore, it has avoided the stalling problem exists in the LBL algorithm. In each iteration step, the weights or thresholds can be optimized directly one by one with other variables fixed. Four classes of solution equations for parameters of networks are deducted. In comparisons with the BP algorithm with momentum (BPM) and the conventional LBL algorithms, NLBL algorithm obtains faster convergences and better simulation performances when applied into a real world oil-gas prediction problem.

作者: Yanlai Li Tao Li Kuanquan Wang

作者单位: School of Computer Science and Technology, Harbin Institute of Technology,Harbin 150001, P.R. China School of Computer Science and Technology, Harbin Institute of Technology,Harbin 150001, P. R. China

会议类型: 国际会议

会议名称: 2011 3rd International Conference on Advanced Computer Control(2011年IEEE第三届高端计算机控制国际会议 ICACC2011)

会议地点: 哈尔滨

会议语种:英文

页码: 600-603

在线出版日期: 2011-01-18（万方平台首次上网日期，不代表论文的发表时间）