Learning One Convolutional Layer with Overlapping Patches

ICML, pp. 1778-1786, 2018.

Cited by: 47|Views26
EI

Abstract:

give the first provably efficient algorithm for learning a one hidden layer convolutional network with respect to a general class of (potentially overlapping) patches. Additionally, our algorithm requires only mild conditions on the underlying distribution. prove that our framework captures commonly used schemes from computer vision, in...More

Code:

Data:

Your rating :
0

 

Tags
Comments