Learning One Convolutional Layer with Overlapping Patches
ICML, pp. 1778-1786, 2018.
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
PPT (Upload PPT)