Learning Neural Networks with Two Nonlinear Layers in Polynomial Time

Surbhi Goel
Surbhi Goel

conference on learning theory, 2019.

Cited by: 54|Views29
EI

Abstract:

We give a polynomial-time algorithm for learning neural networks with one layer of sigmoids feeding into any Lipschitz, monotone activation function (e.g., sigmoid or ReLU). We make no assumptions on the structure of the network, and the algorithm succeeds with respect to {em any} distribution on the unit ball in $n$ dimensions (hidden we...More

Code:

Data:

Your rating :
0

 

Tags
Comments