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

How to develop slim and accurate deep neural networks has become crucial forreal- world applications, especially for those employed in embedded systems.Though previous work along this research line has shown some promising results,most existing methods either fail to significantly compress a well-trained deepnetwork or require a heavy retraining process for the pruned deep network tore-boost its prediction performance. In this paper, we propose a new layer-wisepruning method for deep neural networks. In our proposed method, parameters ofeach individual layer are pruned independently based on second orderderivatives of a layer-wise error function with respect to the correspondingparameters. We prove that the final prediction performance drop after pruningis bounded by a linear combination of the reconstructed errors caused at eachlayer. Therefore, there is a guarantee that one only needs to perform a lightretraining process on the pruned network to resume its original predictionperformance. We conduct extensive experiments on benchmark datasets todemonstrate the effectiveness of our pruning method compared with severalstate-of-the-art baseline methods.

Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon