Engineering Uncertainty Estimation in Neural Networks

Re:Engineering Uncertainty Estimation in Neural Networks by syntaxing on Monday April 15, 2019 @05:17PM (#19669007)

Super interesting. I've been wanting to play around with BNNs after reading Yarin Gal's post on it [1] but my knowledge is limited on how to make it work. Does anyone here have a library or tutorial they recommend using Pytorch?

[1] http://mlg.eng.cam.ac.uk/yarin/blog_3d801aa532c1ce.html

[ Parent | on HN ]

Re:Engineering Uncertainty Estimation in Neural Networks by maiybe on Monday April 15, 2019 @08:30PM (#19670075)

I'd check out Pyro, a probabilistic programming language built on Pytorch.

You can find Bayesian Neural Network examples starting here: http://pyro.ai/examples/bayesian_regression.html

I think the documentation and tutorials are thorough and laid out well to ease you into Bayesian NN and generally handling uncertainty with Neural Networks + Distributions. There's some Pyro-specific constructs in there, but it's the easiest way to get into BNNs without lots of prior knowledge.

[ Parent | on HN ]

Re:Engineering Uncertainty Estimation in Neural Networks by thess24 on Tuesday April 16, 2019 @12:11AM (#19671079)

https://twiecki.io/blog/2016/06/01/bayesian-deep-learning/

This is a good example. There’s not much info I’ve been able to find - I’d be interested if anyone else has a solid tutorial.

[ Parent | on HN ]