Deep convolutional neural networks on cartoon functions

  title={Deep convolutional neural networks on cartoon functions},
  author={Philipp Grohs and Thomas Wiatowski and Helmut B{\"o}lcskei},
  journal={2016 IEEE International Symposium on Information Theory (ISIT)},
Wiatowski and Bölcskei, 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… CONTINUE READING
Related Discussions
This paper has been referenced on Twitter 20 times. VIEW TWEETS


Publications citing this paper.
Showing 1-10 of 10 extracted citations

Invariance and stability of Gabor scattering for music signals

2017 International Conference on Sampling Theory and Applications (SampTA) • 2017
View 3 Excerpts
Highly Influenced

Deformation Stability of Deep Convolutional Neural Networks on Sobolev Spaces

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2018
View 1 Excerpt

Energy decay and conservation in deep convolutional neural networks

2017 IEEE International Symposium on Information Theory (ISIT) • 2017


Publications referenced by this paper.
Showing 1-10 of 17 references

Group Invariant Scattering

ArXiv • 2011
View 4 Excerpts
Highly Influenced

Deep Residual Learning for Image Recognition

2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2016
View 1 Excerpt

Representation Learning: A Review and New Perspectives

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2013
View 1 Excerpt

What is the best multi-stage architecture for object recognition?

2009 IEEE 12th International Conference on Computer Vision • 2009
View 1 Excerpt

Caltech-256 object category dataset

G. Griffin, A. Holub, P. Perona, 2007. • 2007
View 2 Excerpts

Similar Papers

Loading similar papers…