Uncertainty Propagation in Convolutional Neural Networks: Technical Report

02/11/2021
by   Christos Tzelepis, et al.
0

In this technical report we study the problem of propagation of uncertainty (in terms of variances of given uni-variate normal random variables) through typical building blocks of a Convolutional Neural Network (CNN). These include layers that perform linear operations, such as 2D convolutions, fully-connected, and average pooling layers, as well as layers that act non-linearly on their input, such as the Rectified Linear Unit (ReLU). Finally, we discuss the sigmoid function, for which we give approximations of its first- and second-order moments, as well as the binary cross-entropy loss function, for which we approximate its expected value under normal random inputs.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 3

page 4

12/30/2017

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

Recently the generalisation error of deep neural networks has been analy...
10/21/2020

Voronoi Convolutional Neural Networks

In this technical report, we investigate extending convolutional neural ...
04/07/2020

The relationship between Fully Connected Layers and number of classes for the analysis of retinal images

This paper experiments with the number of fully-connected layers in a de...
08/06/2020

Structured Convolutions for Efficient Neural Network Design

In this work, we tackle model efficiency by exploiting redundancy in the...
10/02/2018

GINN: Geometric Illustration of Neural Networks

This informal technical report details the geometric illustration of dec...
03/20/2017

Second-order Convolutional Neural Networks

Convolutional Neural Networks (CNNs) have been successfully applied to m...
09/26/2018

Rediscovering Deep Neural Networks in Finite-State Distributions

We propose a new way of thinking about deep neural networks, in which th...

Code Repositories

uacnn

Uncertainty-Aware CNN - Uncertainty propagation in CNN


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.