Discrete deep feature extraction: A theory and new architectures


Thomas Wiatowski, Michael Tschannen, Aleksandar Stanić, Philipp Grohs, and Helmut Bölcskei


Proc. of International Conference on Machine Learning (ICML), New York, USA, pp. 2149-2158, June 2016.

[BibTeX, LaTeX, and HTML Reference]


First steps towards a mathematical theory of deep convolutional neural networks for feature extraction were made---for the continuous-time case---in Mallat, 2012, and Wiatowski and Bölcskei, 2015. This paper considers the discrete case, introduces new convolutional neural network architectures, and proposes a mathematical framework for their analysis. Specifically, we establish deformation and translation sensitivity results of local and global nature, and we investigate how certain structural properties of the input signal are reflected in the corresponding feature vectors. Our theory applies to general filters and general Lipschitz-continuous non-linearities and pooling operators. Experiments on handwritten digit classification and facial landmark detection---including feature importance evaluation---complement the theoretical findings.

Code to reproduce the figures in this paper is available here.

Download this document:


Copyright Notice: © 2016 T. Wiatowski, M. Tschannen, A. Stanić, P. Grohs, and H. Bölcskei.

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.