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

Symmetry is omnipresent in nature and perceived by the visual system of manyspecies, as it facilitates detecting ecologically important classes of objectsin our environment. Symmetry perception requires abstraction of long-rangespatial dependencies between image regions, and its underlying neuralmechanisms remain elusive. In this paper, we evaluate Deep Neural Network (DNN)architectures on the task of learning symmetry perception from examples. Wedemonstrate that feed-forward DNNs that excel at modelling human performance onobject recognition tasks, are unable to acquire a general notion of symmetry.This is the case even when the DNNs are architected to capture long-rangespatial dependencies, such as through `dilated' convolutions and the recentlyintroduced `transformers' design. By contrast, we find that recurrentarchitectures are capable of learning to perceive symmetry by decomposing thelong-range spatial dependencies into a sequence of local operations, that arereusable for novel images. These results suggest that recurrent connectionslikely play an important role in symmetry perception in artificial systems, andpossibly, biological ones too.

Symmetry Perception by Deep Networks: Inadequacy of Feed-Forward Architectures and Improvements with Recurrent Connections