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

Rectifier neuron units (ReLUs) have been widely used in deep convolutionalnetworks. An ReLU converts negative values to zeros, and does not changepositive values, which leads to a high sparsity of neurons. In this work, wefirst examine the sparsity of the outputs of ReLUs in some popular deepconvolutional architectures. And then we use the sparsity property of ReLUs toaccelerate the calculation of convolution by skipping calculations ofzero-valued neurons. The proposed sparse convolution algorithm achieves somespeedup improvements on CPUs compared to the traditional matrix-matrixmultiplication algorithm for convolution when the sparsity is not less than0.9.

Speeding up Convolutional Neural Networks By Exploiting the Sparsity of Rectifier Units