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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We consider the optimization of deep convolutional neural networks (CNNs)such that they provide good performance while having reduced complexity ifdeployed on either conventional systems with spatial-domain convolution orlower-complexity systems designed for Winograd convolution. The proposedframework produces one compressed model whose convolutional filters can be madesparse either in the spatial domain or in the Winograd domain. Hence, thecompressed model can be deployed universally on any platform, without need forre-training on the deployed platform. To get a better compression ratio, thesparse model is compressed in the spatial domain that has a fewer number ofparameters. From our experiments, we obtain $24.2\times$ and $47.7\times$compressed models for ResNet-18 and AlexNet trained on the ImageNet dataset,while their computational cost is also reduced by $4.5\times$ and $5.1\times$,respectively.

Jointly Sparse Convolutional Neural Networks in Dual Spatial-Winograd Domains