Posit AI Blog: You sure? A Bayesian approach to obtaining uncertainty estimates from neural networksYou sure? A Bayesian approach to obtaining uncertainty estimates from neural networks In deep learning, there is no obvious way of obtaining uncertainty estimates. In 2016, Gal and Ghahramani proposed a method that is both theoretically grounded and practical: use dropout at test time. In this post, we introduce a refined version of this method (Gal et al. 2017) that has the network itself learn h
https://rstudio.github.io/keras/
