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

On-device training is essential for user personalisation and privacy. Withthe pervasiveness of IoT devices and microcontroller units (MCU), this taskbecomes more challenging due to the constrained memory and compute resources,and the limited availability of labelled user data. Nonetheless, prior worksneglect the data scarcity issue, require excessively long training time (e.g. afew hours), or induce substantial accuracy loss ($\geq$10\%). We proposeTinyTrain, an on-device training approach that drastically reduces trainingtime by selectively updating parts of the model and explicitly coping with datascarcity. TinyTrain introduces a task-adaptive sparse-update method thatdynamically selects the layer/channel based on a multi-objective criterion thatjointly captures user data, the memory, and the compute capabilities of thetarget device, leading to high accuracy on unseen tasks with reducedcomputation and memory footprint. TinyTrain outperforms vanilla fine-tuning ofthe entire network by 3.6-5.0\% in accuracy, while reducing the backward-passmemory and computation cost by up to 2,286$\times$ and 7.68$\times$,respectively. Targeting broadly used real-world edge devices, TinyTrainachieves 9.5$\times$ faster and 3.5$\times$ more energy-efficient training overstatus-quo approaches, and 2.8$\times$ smaller memory footprint than SOTAapproaches, while remaining within the 1 MB memory envelope of MCU-gradeplatforms.

TinyTrain: Deep Neural Network Training at the Extreme Edge