News for hackers. Stuff that matters.
Re:Why does deep and cheap learning work so well? by blueprint on Friday May 11, 2018 @05:54PM (#17051036)
Same reason general relativity works. If you try to model results without a fundamental principle of the system's content's operation then you are going to have some limitations.
Re:Why does deep and cheap learning work so well? by nonbel on Friday May 11, 2018 @07:58PM (#17051593)
>"Same reason general relativity works."

Dark matter/energy?

Re:Why does deep and cheap learning work so well? by contravariant on Friday May 11, 2018 @09:17PM (#17051933)
Well, technically general relativity has no real problems with either of those (there shouldn't be, given that general relativity is the main justification for both). It's the quantum mechanics behind them that's not really well understood.
Re:Why does deep and cheap learning work so well? by nonbel on Saturday May 12, 2018 @10:57AM (#17054322)
>"the quantum mechanics behind them that's not really well understood."

I've never heard of it being understood at all.

Re:Why does deep and cheap learning work so well? by blueprint on Saturday May 12, 2018 @08:12AM (#17053685)
They're posited as a fudge factor -because- the quantum mechanics is not understood.
Re:Why does deep and cheap learning work so well? by blueprint on Saturday May 12, 2018 @08:03AM (#17053640)
Well that's actually my point, you are the one who got it