Towards Learning Convolutions from Scratch

[0]

NIPS 2020, 2020.

Cited by: 1|Views16

Keywords:

architecture searchconvolutional neural networkgabor filtergeneral purposeconvolutional networkMore(6+)

Weibo:

We studied the inductive bias of convolutional networks through empirical investigations and Minimum Description Length theory

Abstract:

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

Code:

Data:

Full Text

View via Publisher