Re:Why does deep and cheap learning work so well?
by derefr on Friday May 11, 2018 @06:01PM
(#17051053)
I think the GP poster meant to contrast this paper not with other papers, but with the junk explanations for "how deep learning works" that science journalism comes up with.
[ Parent
| on HN ]
Re:Why does deep and cheap learning work so well?
by mathinpens on Friday May 11, 2018 @06:33PM
(#17051206)
trust me some of the junk explanations for how deep learning works originate from researchers. we really just don't have a convincing picture about why these networks work or don't work in a theoretical way rather than empirical/heuristic handwaves
Re:Why does deep and cheap learning work so well?
by crb002 on Friday May 11, 2018 @07:20PM
(#17051406)
Bollocks see my comment. We know worst case bounds for Kolmogorov random transformations of a finite set, the most complex learning task there is.
Re:Why does deep and cheap learning work so well?
by mathinpens on Friday May 11, 2018 @07:33PM
(#17051466)
huh? not even wrong......