Near Optimal Learning Rate BP Algorithm and Its Application in Traffic Forecast

摘要：

　　Aimed at the inadequacy of the standard BP algorithm,a near optimal learning rate BP algorithm (NOLRBP) is presented.Selecting the learning rate of the algorithm based on one-dimensional search algorithm of optimization theory avoids the blindness in determining the learning rate.Simulations show that the algorithm is superior to the standard BP algorithm (SDBP),momentum BP algorithm (MOBP) and variable learning rate BP algorithm (VLBP).

关键词： Neural Network BP Algorithm Near Optimal Learning Rate One-dimensional Search

作者: Liming Qin Haitao Zhang

作者单位: Electronic & Information Engineering College, Henan University of Science and Technology,Luoyang,Henan,471003,China

会议类型: 国际会议

会议名称: the Second International Conference on Frontiers of Manufacturing and Design Science(第二届制造与设计科学国际会议(ICFMD 2011))

会议地点: 台湾

会议语种:英文

页码: 4513-4517

在线出版日期: 2011-12-11（万方平台首次上网日期，不代表论文的发表时间）