You 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
![Posit AI Blog: You sure? A Bayesian approach to obtaining uncertainty estimates from neural networks](https://cdn-ak-scissors.b.st-hatena.com/image/square/b5902224da4809d4e76b09c881dc52ae93f52860/height=288;version=1;width=512/https%3A%2F%2Fblogs.rstudio.com%2Ftensorflow%2Fposts%2F2018-11-12-uncertainty_estimates_dropout%2Fimages%2Fthumb.png)