Go Deep or Go Home?

Go Deep or Go Home?

den Heijer, Remco (TU Delft Electrical Engineering, Mathematics and Computer Science)

Viering, T.J. (mentor)
Kato, Y. (mentor)
Turan, O.T. (mentor)
Wang, Z. (mentor)
Loog, M. (mentor)
Tax, D.M.J. (mentor)

Delft University of Technology

Computer Science and Engineering

CSE3000 Research Project

2021-07-02

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.

deep learning
Convolutional Neural Networks (CNNs)
Pattern Recognition

http://resolver.tudelft.nl/uuid:56da895a-56a4-4214-ad62-c0aad107830b

Student theses

bachelor thesis

© 2021 Remco den Heijer