PAC-Bayesian Margin Bounds for Convolutional Neural Networks - Technical Report

Pitas Konstantinos, Mike Davies, Pierre Vandergheynst

Research output: Working paper


Recently the generalisation error of deep neural networks has been analysed through the PAC-Bayesian framework, for the case of fully connected layers. We adapt this approach to the convolutional setting.
Original languageUndefined/Unknown
Publication statusPublished - 30 Dec 2017


  • cs.LG
  • stat.ML

Cite this