English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The purpose of this short and simple note is to clarify a commonmisconception about convolutional neural networks (CNNs). CNNs are made up ofconvolutional layers which are shift equivariant due to weight sharing.However, convolutional layers are not translation equivariant, even whenboundary effects are ignored and when pooling and subsampling are absent. Thisis because shift equivariance is a discrete symmetry while translationequivariance is a continuous symmetry. This fact is well known amongresearchers in equivariant machine learning, but is usually overlooked amongnon-experts. To minimize confusion, we suggest using the term `shiftequivariance' to refer to discrete shifts in pixels and `translationequivariance' to refer to continuous translations.

Convolutional layers are equivariant to discrete shifts but not continuous translations