Maximum entropy learning with deep belief networks

Payton Lin, Szu Wei Fu, Syu Siang Wang, Ying Hui Lai, Yu Tsao*

*此作品的通信作者

研究成果: Article同行評審

8 引文 斯高帕斯(Scopus)

摘要

Conventionally, the maximum likelihood (ML) criterion is applied to train a deep belief network (DBN). We present a maximum entropy (ME) learning algorithm for DBNs, designed specifically to handle limited training data. Maximizing only the entropy of parameters in the DBN allows more effective generalization capability, less bias towards data distributions, and robustness to over-fitting compared to ML learning. Results of text classification and object recognition tasks demonstrate ME-trained DBN outperforms ML-trained DBN when training data is limited.

原文English
文章編號251
期刊Entropy
18
發行號7
DOIs
出版狀態Published - 7月 2016

指紋

深入研究「Maximum entropy learning with deep belief networks」主題。共同形成了獨特的指紋。

引用此