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

In this paper, we introduce a new channel pruning method to accelerate verydeep convolutional neural networks. Given a trained CNN model, we propose aniterative two-step algorithm to effectively prune each layer, by a LASSOregression based channel selection and least square reconstruction. We furthergeneralize this algorithm to multi-layer and multi-branch cases. Our methodreduces the accumulated error and enhances the compatibility with variousarchitectures. Our pruned VGG-16 achieves the state-of-the-art results by 5xspeed-up along with only 0.3% increase of error. More importantly, our methodis able to accelerate modern networks like ResNet, Xception and suffers only1.4%, 1.0% accuracy loss under 2x speed-up respectively, which is significant.Our code has been made publicly available.

Pruning Very Deep Neural Network Channels for Efficient Inference