基于自编码特征提取及弹性学习的手写数字识别  

HNR based on autoencoder feature extraction and resilient back propagation

作　　者：姜芳芳[1] 何明一[1] 王欣欣[1] 

机构地区：[1]西北工业大学电子信息学院,陕西西安710129

出　　处：《现代电子技术》2014年第10期31-34,共4页Modern Electronics Technique

摘　　要：针对自编码算法提取输入特征能更好地发现样本间的相关性的优点,以自编码算法提取待识别样本特征作为多层前向网络的输入,以弹性BP算法训练网络,并用MNIST手写数字数据库样本测试。从正确率、拒识率、错误率和可靠率4项性能指标方面与逐像素方法进行了综合对比测试。研究表明,采用自编码特征提取、多层前向神经网络作为分类器以及弹性BP算法进行训练的手写数字识别,具有更快的收敛速度和更高的识别可靠率。As the autoencoder algorithm for input feature extraction is better in discovering the correlation between sam-ples,an new approach is proposed for handwriting number recognition（HNR）,in which the autoencoder algorithm is taken to extract the feature under recognition as the input of multilayer feedforward network,resilient back propagation（BP）algorithm is emplored to train the classifer,and some saples chosen from MNIST handwriting digits database are used to test the performance of this new approach. A comprehensive comparisons between this new approach and the pixel-by-pixel method is coducted in cor-rect rate,rejection rate,error rate and reliability rate. This study results show that the proposed new approach（the autoencoder feature extraction,multilayer feedforward neural network classifier and resilient back propagation training algorithm are used to-gether）has faster training speed and higher recognition reliability.

关 键 词：多层前向神经网络 自编码算法 弹性BP算法 MNIST数据库 

分 类 号：TN911-34[电子电信—通信与信息系统] TP183[电子电信—信息与通信工程]