Hacker News new | ask | show | jobs
by Solvency 1099 days ago
Why couldn't mathematical proofs/models have predicted or revealed this to be the case back then?
2 comments
nurbsnn 1099 days ago
On the contrary, there was a mathematical proof that one-hidden-layer neural network with nonlinearity is enough to represent any function. Using more than 1 hidden seemed a waste.

https://en.wikipedia.org/wiki/Universal_approximation_theore...

link
actionfromafar 1099 days ago
How??
link