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

In this paper, we propose a novel network training mechanism called "dynamicchannel propagation" to prune the neural networks during the training period.In particular, we pick up a specific group of channels in each convolutionallayer to participate in the forward propagation in training time according tothe significance level of channel, which is defined as channel utility. Theutility values with respect to all selected channels are updated simultaneouslywith the error back-propagation process and will adaptively change.Furthermore, when the training ends, channels with high utility values areretained whereas those with low utility values are discarded. Hence, ourproposed scheme trains and prunes neural networks simultaneously. Weempirically evaluate our novel training scheme on various representativebenchmark datasets and advanced convolutional neural network (CNN)architectures, including VGGNet and ResNet. The experiment results verify thesuperior performance and robust effectiveness of our approach.

Learning to Prune in Training via Dynamic Channel Propagation