Re:Why deep learning works even though it shouldn’t
by jellyksong on Tuesday October 20, 2020 @07:31PM
(#24843363)
This article is about optimization (finding good parameters), not the approximation power of neural networks (which is well-known through the universal approximation theorem).
[ Parent
| on HN ]
Re:Why deep learning works even though it shouldn’t
by RandyRanderson on Tuesday October 20, 2020 @09:39PM
(#24844080)
I know. What we're both saying is: if you have enough lines, you can find the params easily.