Sign in

Towards a General Theory of Infinite-Width Limits of Neural Classifiers

By Eugene Golikov
Obtaining theoretical guarantees for neural networks training appears to be a hard problem in a general case. Recent research has been focused on studying this problem in the limit of infinite width and two different theories have been developed: a mean-field (MF) and a constant kernel (NTK) limit theories. We... Show more
June 29, 2020
=
0
Loading PDF…
Loading full text...
Similar articles
Loading recommendations...
=
0
x1
Towards a General Theory of Infinite-Width Limits of Neural Classifiers
Click on play to start listening