Tweeted By @jaschasd

Bayesian CNNs with many channels are Gaussian processes! One can compute test set predictions that would have resulted from fully Bayesian training of a CNN, but without ever instantiating a CNN, and instead by evaluating the corresponding GP. https://t.co/VOdpOKRE5g pic.twitter.com/5Rr9jiLJWW

— Jascha (@jaschasd) October 12, 2018