Re:What Is Temperature in NLP?
by janalsncm on Monday March 13, 2023 @02:28PM
(#35140222)
We don’t use neural networks because they’re a priori the most accurate models of physical processes. We use them because they have two interesting properties:
1) They’re arbitrary function approximators.
2) We have a great way of fitting them to data (backpropagation).
As an aside, it’s just an accident of nature (or is it?) that neural networks have passing similarity to biological systems.
Anyways, it doesn’t make much sense to try to reason about what a neural net is doing inside. What it’s doing is trying to approximate the function it was trained to. That’s it.
1) They’re arbitrary function approximators.
2) We have a great way of fitting them to data (backpropagation).
As an aside, it’s just an accident of nature (or is it?) that neural networks have passing similarity to biological systems.
Anyways, it doesn’t make much sense to try to reason about what a neural net is doing inside. What it’s doing is trying to approximate the function it was trained to. That’s it.