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

Convolutional Neural Network (CNN) is more and more widely used in variousfileds, and its computation and memory-demand are also increasingsignificantly. In order to make it applicable to limited conditions such asembedded application, network compression comes out. Among them, researcherspay more attention to network pruning. In this paper, we encode the convolutionnetwork to obtain the similarity of different encoding nodes, and evaluate theconnectivity-power among convolutional kernels on the basis of the similarity.Then impose different level of penalty according to differentconnectivity-power. Meanwhile, we propose Channel Pruning base on theDissimilarity of Angle (DACP). Firstly, we train a sparse model by GL penalty,and impose an angle dissimilarity constraint on the channels and filters ofconvolutional network to obtain a more sparse structure. Eventually, theeffectiveness of our method is demonstrated in the section of experiment. OnCIFAR-10, we reduce 66.86% FLOPs on VGG-16 with 93.31% accuracy after pruning,where FLOPs represents the number of floating-point operations per second ofthe model. Moreover, on ResNet-32, we reduce FLOPs by 58.46%, which makes theaccuracy after pruning reach 91.76%.

A pruning method based on the dissimilarity of angle among channels and filters