BIOMEDICAL IMAGING GROUP (BIG)
Laboratoire d'imagerie biomédicale (LIB)

Deep Spline Neural Networks

M. Unser, P. Bohra, J. Campos, H. Gupta, S. Aziznejad

Online Seminars on Numerical Approximation and Applications (OSNA2'20), Passau, Federal Republic of Germany, Virtual, November 9-December 3, 2020.

We present a unifying functional framework for the implementation and training of deep neural networks (DNN) with free-form activation functions. To make the problem well posed, we constrain the shape of the trainable activations (neurons) by penalizing their second-order total-variations. We prove that the optimal activations are adaptive piecewise-linear splines, which allows us to recast the problem as a parametric optimization. We then specify some corresponding trainable B-spline-based activation units. These modules can be inserted in deep neural architectures and optimized efficiently using standard tools. We provide experimental results that demonstrate the benefit of our approach. 

@INPROCEEDINGS(http://bigwww.epfl.ch/publications/unser2005.html,
AUTHOR="Unser, M. and Bohra, P. and Campos, J. and Gupta, H. and
	Aziznejad, S.",
TITLE="Deep Spline Neural Networks",
BOOKTITLE="Online Seminars on Numerical Approximation and Applications
	({OSNA2'20})",
YEAR="2020",
editor="",
volume="",
series="",
pages="",
address="Passau, Federal Republic of Germany, Virtual",
month="November 9-December 3,",
organization="",
publisher="",
note="")
© 2020 OSNA2. 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 OSNA2. 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.