Noisy objective functions based on the f-divergence

Markus Nussbaum-Thom,Ralf Schlüter,Vaibhava Goel,Hermann Ney

2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)（2017）

引用 23|浏览87

暂无评分

摘要

Dropout, the random dropping out of activations according to a specified rate, is a very simple but effective method to avoid over-fitting of deep neural networks to the training data.

查看译文

关键词

dropout, generalization error bounds, training criteria, f-divergence, neural networks

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要