Go Deep or Go Home?

Bachelor thesis (2021)

Authors

M.C. den Heijer Electrical Engineering, Mathematics and Computer Science

Contributors

T.J. Viering Computer Science & Engineering-Teaching Team - EEMCS (supervisor 1)
Y. Kato Pattern Recognition and Bioinformatics - EEMCS (supervisor 1)
O.T. Turan Pattern Recognition and Bioinformatics - EEMCS (supervisor 1)
Z. Wang Pattern Recognition and Bioinformatics - EEMCS (supervisor 1)
M. Loog Pattern Recognition and Bioinformatics - EEMCS (supervisor 1)
D.M.J. Tax Pattern Recognition and Bioinformatics - EEMCS (supervisor 1)
Faculty
Electrical Engineering, Mathematics and Computer Science
Copyright: © 2021 Remco den Heijer
Deep learning Pattern Recognition Convolutional Neural Networks (CNNs)
More Info
expand_more

Published Date

02-07-2021

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Electrical Engineering, Mathematics and Computer Science

Abstract

Does a convolutional neural network (CNN) always have to be deep to learn a task? This is an important question as deeper networks are generally harder to train. We trained shallow and deep CNNs and evaluated their performance on simple regression tasks, such as computing the mean pixel value of an image. For these simple tasks we show that going deeper does not guarantee an improvement in performance.