You sure? A Bayesian approach to obtaining uncertainty estimates from neural networks
This article is originally published at https://blogs.rstudio.com/tensorflow/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 how uncertain it is.
Thanks for visiting r-craft.org
This article is originally published at https://blogs.rstudio.com/tensorflow/
Please visit source website for post related comments.