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 present an algorithm-hardware codesign for camera-basedautonomous flight in small drones. We show that the large write-latency andwrite-energy for nonvolatile memory (NVM) based embedded systems makes themunsuitable for real-time reinforcement learning (RL). We address this byperforming transfer learning (TL) on metaenvironments and RL on the last fewlayers of a deep convolutional network. While the NVM stores the meta-modelfrom TL, an on-die SRAM stores the weights of the last few layers. Thus all thereal-time updates via RL are carried out on the SRAM arrays. This provides uswith a practical platform with comparable performance as end-to-end RL and83.4% lower energy per image frame

Transfer and Online Reinforcement Learning in STT-MRAM Based Embedded Systems for Autonomous Drones