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

This work aims to enable persistent, event-driven sensing and decisioncapabilities for energy-harvesting (EH)-powered devices by deployinglightweight DNNs onto EH-powered devices. However, harvested energy is usuallyweak and unpredictable and even lightweight DNNs take multiple power cycles tofinish one inference. To eliminate the indefinite long wait to accumulateenergy for one inference and to optimize the accuracy, we developed a powertrace-aware and exit-guided network compression algorithm to compress anddeploy multi-exit neural networks to EH-powered microcontrollers (MCUs) andselect exits during execution according to available energy. The experimentalresults show superior accuracy and latency compared with state-of-the-arttechniques.

Intermittent Inference with Nonuniformly Compressed Multi-Exit Neural Network for Energy Harvesting Powered Devices