News for hackers. Stuff that matters.
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.

There are no comments on this comment yet.