Re:Why does deep and cheap learning work so well?
by sp332 on Friday May 11, 2018 @06:11PM
(#17051105)
Good. I hope to see more of them posted to HN.
[ Parent
| on HN ]
Re:Why does deep and cheap learning work so well?
by mathinpens on Friday May 11, 2018 @06:27PM
(#17051174)
if you are interested in this type of analysis are you familiar with the tishby papers? you will at the very least find them enjoyable/mind opening...
but some of his key claims are probably contradicted by empirical results.
the original paper: https://arxiv.org/abs/1503.02406
a refutation:(with very harsh/unprofessional words by tishby in counter-refutation)
Re:Why does deep and cheap learning work so well?
by wangii on Saturday May 12, 2018 @06:06AM
(#17053328)
I found his talk on youtube, remarkable:
Re:Why does deep and cheap learning work so well?
by mathinpens on Saturday May 12, 2018 @11:49AM
(#17054598)
He's a good speaker/teacher but I think there are serious problems with his work- mainly that a lot of his results collapse when tested on more general architectures.