English

Understanding Deep Convolutional Networks

Machine Learning 2016-04-27 v1 Computer Vision and Pattern Recognition Machine Learning

Abstract

Deep convolutional networks provide state of the art classifications and regressions results over many high-dimensional problems. We review their architecture, which scatters data with a cascade of linear filter weights and non-linearities. A mathematical framework is introduced to analyze their properties. Computations of invariants involve multiscale contractions, the linearization of hierarchical symmetries, and sparse separations. Applications are discussed.

Keywords

Cite

@article{arxiv.1601.04920,
  title  = {Understanding Deep Convolutional Networks},
  author = {Stéphane Mallat},
  journal= {arXiv preprint arXiv:1601.04920},
  year   = {2016}
}

Comments

17 pages, 4 Figures

R2 v1 2026-06-22T12:32:37.005Z