Maximal function pooling with applications

DOI10.1007/978-3-030-69637-5_21MaRDI QIDQ6361870arXivFDO

Authors Wojciech Czaja, Weilin Li, Yiran Li, Mike Pekala

Publication date 1 March 2021

Published in arXiv

Full work available at URL https://doi.org/10.1007/978-3-030-69637-5_21

Mathematics Subject Classification ID

Maximal functions, Littlewood-Paley theory (42B25) Artificial neural networks and deep learning (68T07)

arXiv classification

cs.CV cs.IT math.IT

Abstract: Inspired by the Hardy-Littlewood maximal function, we propose a novel pooling strategy which is called maxfun pooling. It is presented both as a viable alternative to some of the most popular pooling functions, such as max pooling and average pooling, and as a way of interpolating between these two algorithms. We demonstrate the features of maxfun pooling with two applications: first in the context of convolutional sparse coding, and then for image classification.

This page was built for publication: Maximal function pooling with applications

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6361870)