
Open access
Author
Date
2018Type
- Doctoral Thesis
ETH Bibliography
yes
Altmetrics
Abstract
A central task in machine learning, computer vision, and signal processing is to extract characteristic features of signals. Feature extractors based on deep convolutional neural networks have been applied with significant success in a wide range of practical machine learning tasks such as classification of images in the ImageNet data set, image captioning, or control-policy-learning to play Atari games or the board game Go. Since deep convolutional neural networks lead to remarkable results across a broad range of applications, it is essential to understand their underlying mechanisms. In this thesis, we develop a mathematical theory of deep convolutional neural networks for feature extraction using concepts from applied harmonic analysis. We investigate the impact of network topology and building blocks—convolution filters, non-linearities, and pooling operators—on the network's feature extraction capabilities. Show more
Permanent link
https://doi.org/10.3929/ethz-b-000252349Publication status
publishedExternal links
Search print copy at ETH Library
Publisher
ETH ZurichSubject
Frame theory; Machine learning; Convolutional neural networks; Feature extraction; Deep learningOrganisational unit
03610 - Boelcskei, Helmut / Boelcskei, Helmut
More
Show all metadata
ETH Bibliography
yes
Altmetrics