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

12/30/2017
by   Pitas Konstantinos, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/24/2019

Dichotomize and Generalize: PAC-Bayesian Binary Activated Deep Neural Networks

We present a comprehensive study of multilayer neural networks with bina...
research
07/08/2021

On Margins and Derandomisation in PAC-Bayes

We develop a framework for derandomising PAC-Bayesian generalisation bou...
research
10/12/2020

How does Weight Correlation Affect the Generalisation Ability of Deep Neural Networks

This paper studies the novel concept of weight correlation in deep neura...
research
04/10/2019

Pixel-Adaptive Convolutional Neural Networks

Convolutions are the fundamental building block of CNNs. The fact that t...
research
10/21/2020

Voronoi Convolutional Neural Networks

In this technical report, we investigate extending convolutional neural ...
research
02/11/2021

Uncertainty Propagation in Convolutional Neural Networks: Technical Report

In this technical report we study the problem of propagation of uncertai...
research
04/12/2021

PAC Bayesian Performance Guarantees for Deep (Stochastic) Networks in Medical Imaging

Application of deep neural networks to medical imaging tasks has in some...

Please sign up or login with your details

Forgot password? Click here to reset