Invariance and Stability of Deep Convolutional Representations
Abstract
In this paper, we study deep signal representations that are near-invariant to groups of transformations and stable to the action of diffeomorphisms without losing signal information. This is achieved by generalizing the multilayer kernel introduced in the context of convolutional kernel networks and by studying the geometry of the corresponding reproducing kernel Hilbert space. We show that the signal representation is stable, and that models from this functional space, such as a large class of convolutional neural networks, may enjoy the same stability.
Cite
Text
Bietti and Mairal. "Invariance and Stability of Deep Convolutional Representations." Neural Information Processing Systems, 2017.Markdown
[Bietti and Mairal. "Invariance and Stability of Deep Convolutional Representations." Neural Information Processing Systems, 2017.](https://mlanthology.org/neurips/2017/bietti2017neurips-invariance/)BibTeX
@inproceedings{bietti2017neurips-invariance,
title = {{Invariance and Stability of Deep Convolutional Representations}},
author = {Bietti, Alberto and Mairal, Julien},
booktitle = {Neural Information Processing Systems},
year = {2017},
pages = {6210-6220},
url = {https://mlanthology.org/neurips/2017/bietti2017neurips-invariance/}
}