PAC-Bayesian Margin Bounds for Convolutional Neural Networks

2017-12-30Code Available0· sign in to hype

Konstantinos Pitas, Mike Davies, Pierre Vandergheynst

Code Available — Be the first to reproduce this paper.

Code

github.com/konstantinos-p/PAC_Bayesian_Generalization
tf★ 2

Abstract

Recently the generalization error of deep neural networks has been analyzed through the PAC-Bayesian framework, for the case of fully connected layers. We adapt this approach to the convolutional setting.

PAC-Bayesian Margin Bounds for Convolutional Neural Networks

Code

Abstract

Reproductions