Learnable Bernoulli Dropout for Bayesian Deep Learning
AISTATS, pp. 3905-3916, 2020.
In this work, we propose learnable Bernoulli dropout (LBD), a new model-agnostic dropout scheme that considers the dropout rates as parameters jointly optimized with other model parameters. By probabilistic modeling of Bernoulli dropout, our method enables more robust prediction and uncertainty quantification in deep models. Especially,...More
PPT (Upload PPT)