Re:Deep Learning's Diminishing Returns
by andreyk on Friday September 24, 2021 @07:42PM
(#28649009)
The whole point is weird - having more equations than unknowns is only needed for an exact closed form solution, it's entirely possible to solve underconstrained problems that have multiple solutions via optimization (which is what DL is). To be fair, the article says just that afterward, just weird that the high school thing was mentioned in the first place.
[ Parent
| on HN ]
There are no comments on this comment yet.