You can manage bookmarks using lists, please log in to your user account for this.
Media type:
E-Article
Title:
Understanding deep convolutional networks
Contributor:
Mallat, Stéphane
imprint:
The Royal Society, 2016
Published in:Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences
Language:
English
DOI:
10.1098/rsta.2015.0203
ISSN:
1364-503X;
1471-2962
Origination:
Footnote:
Description:
<jats:p>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 nonlinearities. A mathematical framework is introduced to analyse their properties. Computations of invariants involve multiscale contractions with wavelets, the linearization of hierarchical symmetries and sparse separations. Applications are discussed.</jats:p>