Adding uncertainty estimates to Keras models with tfprobability
This article is originally published at https://blogs.rstudio.com/tensorflow/As of today, there is no mainstream road to obtaining uncertainty estimates from neural networks. All that can be said is that, normally, approaches tend to be Bayesian in spirit, involving some way of putting a prior over model weights. This holds true as well for the method presented in this post: We show how to use tfprobability, the R interface to TensorFlow Probability, to add uncertainty estimates to a Keras model in an elegant and conceptually plausible way.
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.
