News for hackers. Stuff that matters.

A comment on Making a neural network say “I Don’t Know”: Bayesian NNs using Pyro and PyTorch. Parent comment

Re:Making a neural network say “I Don’t Know”: Bayesian NNs ... by dmurray on Wednesday November 28, 2018 @12:49PM (#18553734)
Yes, this is buried deeply in the article, but the classifier rejected 12% of the handwritten digits - and did not even have good accuracy when forced to guess on those 12%.
[ Parent | on HN ]

There are no comments on this comment yet.