Re:Failures of Deep Learning
by LeanderK on Friday March 24, 2017 @05:54PM
(#13952548)
I strongly dissagree. Broken down, Neural Networks are surprisingly simpel and elegant. The combination makes them so powerful. Ideally, an elegant theory would abstract over these to provide bounds for arbitrary combinations, or groups of combinations.
[ Parent
| on HN ]
There are no comments on this comment yet.