pasquale caterino

> Hi @Rockdeldiablo, > > I think it's based on the method known as Bayes by Backprop ([Blundell et al., 2015](https://arxiv.org/abs/1505.05424)). thanks

@pat-alt ok this one passes the tests but i don't want it to be merged yet for some reasons: 1) there is a small function that is still missing 2)...

> Let me know when you're happy for this to be merged, then I'll review one more time @pasq-cat try this version pls. i had to add seed to the...

https://web.ics.purdue.edu/~lewicki/physics218/significant#:~:text=(1)%20The%20number%20of%20significant,when%20stating%20the%20experimental%20uncertainty. https://en.wikipedia.org/wiki/Significant_figures#Writing_uncertainty_and_implied_uncertainty @pat-alt it just doesn't make sense to ask the computer to create a probability distribution with a variance with a huge number of digits when you are already...

@pat-alt i will just create an example of what i think should be done in this branch.

@pat-alt ok it requires a major overhaul and the juice isn't worth the squeeze. i guess we can close this issue.

> Sure? Seems like rounding shouldn't require too much of an overhaul? I'm happy to keep this open and just park it for now (could be good one to pick...

> Got it! Maybe we can just print the rounded values? Might be an overkill though, so also happy to close this if someone uses it on a huge dataset...

mah. if i had a black box and i wanted to have an idea of where it is uncertain i would not omit the contribution of either epistemic and aleatoric...

the end results should look like this for a miscalibrated network  and like this for a calibrated network