Towards Learning Convolutions from Scratch
NIPS 2020, 2020.
We studied the inductive bias of convolutional networks through empirical investigations and Minimum Description Length theory
Convolution is one of the most essential components of architectures used in computer vision. As machine learning moves towards reducing the expert bias and learning it from data, a natural next step seems to be learning convolution-like structures from scratch. This, however, has proven elusive. For example, current state-of-the-art ar...More
PPT (Upload PPT)