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

We characterize convolutional neural networks with respect to the relativeamount of features per layer. Using a skew normal distribution as aparametrized framework, we investigate the common assumption of monotonouslyincreasing feature-counts with higher layers of architecture designs. Ourevaluation on models with VGG-type layers on the MNIST, Fashion-MNIST andCIFAR-10 image classification benchmarks provides evidence that motivatesrethinking of our common assumption: architectures that favor larger earlylayers seem to yield better accuracy.

Rethinking Layer-wise Feature Amounts in Convolutional Neural Network Architectures