Deep Convolutional Neural Networks on Cartoon Functions


METADATA ONLY
Loading...

Date

2016-04

Publication Type

Report

ETH Bibliography

yes

Citations

Altmetric
METADATA ONLY

Data

Rights / License

Abstract

Wiatowski and B\"olcskei, 2015, proved that deformation stability and vertical translation invariance of deep convolutional neural network-based feature extractors are guaranteed by the network structure per se rather than the specific convolution kernels and non-linearities. While the translation invariance result applies to square-integrable functions, the deformation stability bound holds for band-limited functions only. Many signals of practical relevance (such as natural images) exhibit, however, sharp and curved discontinuities and are hence not band-limited. The main contribution of this paper is a deformation stability result that takes these structural properties into account. Specifically, we establish deformation stability bounds for the class of cartoon functions introduced by Donoho, 2001.

Publication status

published

Editor

Book title

Volume

2016-25

Pages / Article No.

Publisher

Seminar for Applied Mathematics, ETH Zurich

Event

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Organisational unit

03941 - Grohs, Philipp (ehemalig) check_circle

Notes

Funding

Related publications and datasets

Is previous version of: