An improved dropout method and its application into DBN-based handwriting recognition

Guangzheng Hu, Huifang Li, Lixuan Luo, Yuanqing Xia

科研成果: 书/报告/会议事项章节会议稿件同行评审

7 引用 (Scopus)

摘要

As a typical deep learning method, Deep Belief Network (DBN) and Dropout method are usually used together for pattern recognition in case of lacking training data. Dropout training can avoid the overfitting phenomenon in deep neural network. During the testing stage, the outputs of all neurons in hidden layers are multiplied by a same factor as their actual outputs in the original Dropout method. It does not consider that the participation of a few poor-recognition models may reduce the recognition accuracy of its whole DBN model. This paper proposed an improved Dropout method, which can further increase the recognition accuracy of DBN by introducing probability statistics. The comparison of recognition results for MNIST handwritten digit database shows that the improved method can outperform the original and traditional identification methods under the same conditions.

源语言英语
主期刊名Proceedings of the 36th Chinese Control Conference, CCC 2017
编辑Tao Liu, Qianchuan Zhao
出版商IEEE Computer Society
11145-11149
页数5
ISBN(电子版)9789881563934
DOI
出版状态已出版 - 7 9月 2017
活动36th Chinese Control Conference, CCC 2017 - Dalian, 中国
期限: 26 7月 201728 7月 2017

出版系列

姓名Chinese Control Conference, CCC
ISSN(印刷版)1934-1768
ISSN(电子版)2161-2927

会议

会议36th Chinese Control Conference, CCC 2017
国家/地区中国
Dalian
时期26/07/1728/07/17

指纹

探究 'An improved dropout method and its application into DBN-based handwriting recognition' 的科研主题。它们共同构成独一无二的指纹。

引用此