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/

Zendy Plus

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

Zendy Tools

Zendy Open

Recently, deep neural networks (DNNs) have been widely applied in mobileintelligent applications. The inference for the DNNs is usually performed inthe cloud. However, it leads to a large overhead of transmitting data viawireless network. In this paper, we demonstrate the advantages of thecloud-edge collaborative inference with quantization. By analyzing thecharacteristics of layers in DNNs, an auto-tuning neural network quantizationframework for collaborative inference is proposed. We study the effectivenessof mixed-precision collaborative inference of state-of-the-art DNNs by usingImageNet dataset. The experimental results show that our framework can generatereasonable network partitions and reduce the storage on mobile devices withtrivial loss of accuracy.

Auto-tuning Neural Network Quantization Framework for Collaborative Inference Between the Cloud and Edge