Re:A visual proof that neural nets can compute any function
by mjburgess on Sunday March 06, 2022 @01:59PM
(#30580074)
Well, indeed.
One then needs to explain how a NN being a "universal fn approximator" helps at all in this context.
One models RVs generativey using distributions (and so on), the actual model (eg., of house prices) isnt a function, it's often an infinity of them.
Re:A visual proof that neural nets can compute any function
by thfuran on Sunday March 06, 2022 @02:23PM
(#30580303)
>One then needs to explain how a NN being a "universal fn approximator" helps at all in this context.
Given that I can't tell why you don't think it does, I don't think I can explain it to you. From the other contexts you've talked about here, you seem to be implying that the only thing that is potentially useful is an AGI which either carries out or merely designs experiments. But that's patently absurd.
Only if you want to throw away most of the information in your model.