Research reports

Years: 2025 2024 2023 2022 2021 2020 2019 2018 2017 2016 2015 2014 2013 2012 2011 2010 2009 2008 2007 2006 2005 2004 2003 2002 2001 2000 1999 1998 1997 1996 1995 1994 1993 1992 1991

Discrete deep feature extraction: A theory and new architectures

by T. Wiatowski and M. Tschannen and A. Stanic and P. Grohs and H. Bölcskei

(Report number 2016-29)

Abstract
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 B\"olcskei, 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.

Keywords: deep learning, convolutional neural networks, deformation stability

@Techreport{WTSGB16_666,
  author = {T. Wiatowski and M. Tschannen and A. Stanic and P. Grohs and H. B\"olcskei},
  title = {Discrete deep feature extraction: A theory and new architectures},
  institution = {Seminar for Applied Mathematics, ETH Z{\"u}rich},
  number = {2016-29},
  address = {Switzerland},
  url = {https://www.sam.math.ethz.ch/sam_reports/reports_final/reports2016/2016-29.pdf },
  year = {2016}
}

Disclaimer
© Copyright for documents on this server remains with the authors. Copies of these documents made by electronic or mechanical means including information storage and retrieval systems, may only be employed for personal use. The administrators respectfully request that authors inform them when any paper is published to avoid copyright infringement. Note that unauthorised copying of copyright material is illegal and may lead to prosecution. Neither the administrators nor the Seminar for Applied Mathematics (SAM) accept any liability in this respect. The most recent version of a SAM report may differ in formatting and style from published journal version. Do reference the published version if possible (see SAM Publications).