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 convolutional neural networks are generally regarded as robust functionapproximators. So far, this intuition is based on perturbations to externalstimuli such as the images to be classified. Here we explore the robustness ofconvolutional neural networks to perturbations to the internal weights andarchitecture of the network itself. We show that convolutional networks aresurprisingly robust to a number of internal perturbations in the higherconvolutional layers but the bottom convolutional layers are much more fragile.For instance, Alexnet shows less than a 30% decrease in classificationperformance when randomly removing over 70% of weight connections in the topconvolutional or dense layers but performance is almost at chance with the sameperturbation in the first convolutional layer. Finally, we suggest furtherinvestigations which could continue to inform the robustness of convolutionalnetworks to internal perturbations.

On the Robustness of Convolutional Neural Networks to Internal Architecture and Weight Perturbations