Just having heard lately about BNNs (wow, ANNs and CNNs are clear; now there's a B? What's that? Ahh, Bayesian ;-)) and quickly getting their main idea and focus, that is, weights not being pure static numbers anymore, but instead described by a distribution function, allowing the net to be "uncertain" about its answers (for more about BNNs, see, for example, this post, or, if you want to know a lot about them, check out this introduction and survey),

I'm now curious about any practical examples of where BNNs are used nowadays, maybe even more successful than other (deep learning) alternatives?

Thanks to nbro's comment here, pointing out that asking this question is not unknowingly, but relevant.

  • $\begingroup$ Please edit the question to limit it to a specific problem with enough detail to identify an adequate answer. $\endgroup$
    – Community Bot
    Commented Jun 24, 2022 at 0:24
  • $\begingroup$ arxiv.org/pdf/2002.00269.pdf $\endgroup$
    – Daniel
    Commented Jun 24, 2022 at 3:45
  • 1
    $\begingroup$ @Community I am questioning today's practicality of BNNs and asking (see tags) for state-of-the-art and/or references. I think it's clear what I am asking and how an adequate answer would look like. Please correct me if I am mistaken here. $\endgroup$
    – Mathy
    Commented Jun 27, 2022 at 6:36
  • 1
    $\begingroup$ @dangom I skimmed that article but I honestly could not find any real value about my question in it. It's morge like the introduction and survey I linked above; but not about its daily use. $\endgroup$
    – Mathy
    Commented Jun 27, 2022 at 6:41


You must log in to answer this question.