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

Deep artificial neural networks (DNNs) trained through backpropagationprovide effective models of the mammalian visual system, accurately capturingthe hierarchy of neural responses through primary visual cortex to inferiortemporal cortex (IT). However, the ability of these networks to explainrepresentations in higher cortical areas is relatively lacking and considerablyless well researched. For example, DNNs have been less successful as a model ofthe egocentric to allocentric transformation embodied by circuits inretrosplenial and posterior parietal cortex. We describe a novel sceneperception benchmark inspired by a hippocampal dependent task, designed toprobe the ability of DNNs to transform scenes viewed from different egocentricperspectives. Using a network architecture inspired by the connectivity betweentemporal lobe structures and the hippocampus, we demonstrate that DNNs trainedusing a triplet loss can learn this task. Moreover, by enforcing a factorizedlatent space, we can split information propagation into "what" and "where"pathways, which we use to reconstruct the input. This allows us to beat thestate-of-the-art for unsupervised object segmentation on the CATER andMOVi-A,B,C benchmarks.

Probing neural representations of scene perception in a hippocampally dependent task using artificial neural networks