EPFL
 Biomedical Imaging GroupSTI
EPFL
  Publications
English only   BIG > Publications > Deep Networks


 CONTENTS
 Home Page
 News & Events
 People
 Publications
 Tutorials and Reviews
 Research
 Demos
 Download Algorithms

 DOWNLOAD
 PDF not available
 PS not available
 All BibTeX References

Splines and Imaging: From Compressed Sensing to Deep Neural Nets

M. Unser

Plenary talk, Fifteenth Biennial Conference, 2020 International Conference on Signal Processing and Communications (SPCOM'20), Bangalore, Republic of India, July 19-24, 2020.



Our intent is to demonstrate the optimality of splines for the resolution of inverse problems in imaging and the design of deep neural networks. To that end, we first describe a recent representer theorem that states that the extremal points of a broad class of linear inverse problems with generalized total-variation regularization are adaptive splines whose type is linked to the underlying regularization operator L. For instance, when L is n-th derivative (resp., Laplacian) operator, the optimal reconstruction is a non-uniform polynomial (resp., polyharmonic) spline with the smallest possible number of adaptive knots.

The crucial observation is that such continuous-domain solutions are intrinsically sparse, and hence compatible with the kind of formulation (and algorithms) used in compressed sensing.

We then make the link with current learning techniques by applying the theorem to optimize the shape of individual activations in a deep neural network. By selecting the regularization functional to be the 2nd-order total variation, we obtain an "optimal" deep-spline network whose activations are piecewise-linear splines with a few adaptive knots. Since each spline knot can be encoded with a ReLU unit, this provides a variational justification of the popular ReLU architecture. It also suggests some new computational challenges for the determination of the optimal activations involving linear combinations of ReLUs.


@INPROCEEDINGS(http://bigwww.epfl.ch/publications/unser2002.html,
AUTHOR="Unser, M.",
TITLE="Splines and Imaging: {F}rom Compressed Sensing to Deep Neural
        Nets",
BOOKTITLE="Fifteenth Biennial Conference, 2020 International Conference
        on Signal Processing and Communications ({SPCOM'20})",
YEAR="2020",
editor="",
volume="",
series="",
pages="",
address="Bangalore, Republic of India",
month=" July 19-24,",
organization="",
publisher="",
note="Plenary talk")

© 2020 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from IEEE.
This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.