Re:Wide Neural Networks of Any Architecture Are Gaussian Pro...
by joshvm on Thursday November 28, 2019 @05:35AM
(#21656123)
You can use it to estimate model uncertainty, Yarin Gal has some nice writeups on this: https://www.cs.ox.ac.uk/people/yarin.gal/website/blog_3d801a... (in this case using dropout networks as GP approximations).
[ Parent
| on HN ]
Re:Wide Neural Networks of Any Architecture Are Gaussian Pro...
by PeterisP on Thursday November 28, 2019 @01:12PM
(#21659194)
How would we use a property of networks with random weights to estimate uncertainty of trained models in which which the weights are (as much as we can) trained to be not random?