Re:Deep Learning: A Critical Appraisal [pdf]
by bitL on Saturday January 06, 2018 @04:06AM
(#16084498)
Why do you think it's overhyped? It pushed state-of-art results in quite a few difficult domains by quite high margin; it's deservedly praised. Or you don't like that you can't really understand what is going on inside, despite it using simple math and primitive non-linear optimization, making it "conceptually" inferior and not as "tasty" to other ML methods where we can actually prove something?
[ Parent
| on HN ]
Re:Deep Learning: A Critical Appraisal [pdf]
by yorwba on Saturday January 06, 2018 @06:13AM
(#16084772)
Deep learning is especially overhyped by articles that describe it as "just like the human brain". It's a useful technique that lets you skip lots of feature engineering by just letting the classifier learn its own features, but it is also really easy to project abilities onto neural networks that they don't really have.
Deep learning is not magic, for every network architecture that beats the state of the art, there are a hundred very similar ones that completely fail, or run too slow, or don't fit into GPU memory ... and the only way we know to get improvements is to fiddle with the hyperparameters until everything works out.
Re:Deep Learning: A Critical Appraisal [pdf]
by vadimberman on Saturday January 06, 2018 @11:13PM
(#16089102)
Because today, most lay people equate deep learning with AI.
The black box part is also an issue which both the author of the paper and literally everyone else, including Google's Peter Norvig, is concerned about. But that's not related to the hype part.