Variational Dropout
Variational Dropout is a variational inference method that extends Bayesian dropout by treating dropout rates as learnable parameters within a probabilistic framework, enabling automatic optimization of sparsity during training through stochastic gradient variational inference.
67
Publications
5K
Citations
207
Authors
106
Institutions
Publications per year
2017–2026
56
Parents
67
Crash data augmentation using variational autoencoder
Zubayer Islam, Mohamed Abdel‐Aty, Qing Cai et al. · Accident Analysis & Prevention · 2020 · 204 citations
1–5 of 67
207
4
h-index
4
h-index
2
h-index
MRC Cognition and Brain Sciences Unit, United Kingdom
2 publications · 28 citations
2
h-index
2
h-index
1–5 of 207
106
University of Cambridge
Cambridge, United Kingdom
5 h-index
8 publications
2.1K citations

Beijing University of Posts and Telecommunications
Beijing, China
2 h-index
10 publications
480 citations

Jinan University
Guangzhou, China
2 h-index
2 publications
38 citations

University of Toronto
Toronto, Canada
2 h-index
4 publications
570 citations

University of Warsaw
Warsaw, Poland
2 h-index
6 publications
447 citations

National Research University Higher School of Economics
Moscow, Russia
2 h-index
5 publications
738 citations

Medical University of Warsaw
Warsaw, Poland
2 h-index
2 publications
149 citations
University College London
London, United Kingdom
2 h-index
8 publications
454 citations
1–8 of 106
Repository · 18 publications · 1.6K citations
14
h-index
2 publications · 47 citations
2
h-index
2 publications · 105 citations
2
h-index
Conference · 2 publications · 154 citations
2
h-index
2 publications · 60 citations
2
h-index
1–5