Off-line Handwritten Digit Recognition Based on Improved BP Artificial Neural Network

摘要：

This paper improved the adaptive factor of gradient to improve the transfer function on the base of the means of momentum,aimed at the training difficult to escape the flat area of error.This method had an application on off-line handwritten recognition.The results showed: this method could not only raise precision of BP artificial neural network,but also improve the convergent speed of it.

关键词： BP artificial neural network factor of gradient transfer function off-line handwritten digit recognition

作者: Chengde Zhang Xiangnian Huang

作者单位: School of Mathematics and Computer Engineering,Xihua University,Chengdu,Sichuan,China ,610039

会议类型: 国际会议

会议名称: 2008 IEEE International Conference on Service Operations and Logistics, and Informatics(IEEE/SOLI’2008)(IEEE服务运作、物流与信息年会)

会议地点: 北京

会议语种:英文

在线出版日期: 2008-10-12（万方平台首次上网日期，不代表论文的发表时间）