Re:Why deep learning works even though it shouldn’t
by pmiller2 on Tuesday October 20, 2020 @05:48PM
(#24842684)
Side note: You can fit an elephant with just 1 parameter. See https://twitter.com/exobenelson/status/1001473539789213697 and the paper linked therein.
https://en.wikiquote.org/wiki/John_von_Neumann