Re:Every model learned by gradient descent is approximately ...
by retrac on Sunday February 25, 2024 @10:07AM
(#39501336)
> Surely learning an algorithm is memorization?
Yes. In a sense, every algorithm can be reduced to memorization, where you precalculate all possible inputs to all possible outputs and store them in a giant lookup table.
Yes. In a sense, every algorithm can be reduced to memorization, where you precalculate all possible inputs to all possible outputs and store them in a giant lookup table.