Altitude Training: Strong Bounds for Single-Layer Dropout

ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 27 (NIPS 2014), pp. 100-108, 2014.

被引用40|引用|浏览33
EI
其它链接dblp.uni-trier.de|academic.microsoft.com|arxiv.org

摘要

Dropout training, originally designed for deep neural networks, has been successful on high-dimensional single-layer natural language tasks. This paper proposes a theoretical explanation for this phenomenon: we show that, under a generative Poisson topic model with long documents, dropout training improves the exponent in the generalizati...更多

代码

数据

下载 PDF 全文
您的评分 :
0

 

标签
评论