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

DTMM is a library designed for efficient deployment and execution of machinelearning models on weak IoT devices such as microcontroller units (MCUs). Themotivation for designing DTMM comes from the emerging field of tiny machinelearning (TinyML), which explores extending the reach of machine learning tomany low-end IoT devices to achieve ubiquitous intelligence. Due to the weakcapability of embedded devices, it is necessary to compress models by pruningenough weights before deploying. Although pruning has been studied extensivelyon many computing platforms, two key issues with pruning methods areexacerbated on MCUs: models need to be deeply compressed without significantlycompromising accuracy, and they should perform efficiently after pruning.Current solutions only achieve one of these objectives, but not both. In thispaper, we find that pruned models have great potential for efficient deploymentand execution on MCUs. Therefore, we propose DTMM with pruning unit selection,pre-execution pruning optimizations, runtime acceleration, and post-executionlow-cost storage to fill the gap for efficient deployment and execution ofpruned models. It can be integrated into commercial ML frameworks for practicaldeployment, and a prototype system has been developed. Extensive experiments onvarious models show promising gains compared to state-of-the-art methods.

DTMM: Deploying TinyML Models on Extremely Weak IoT Devices with Pruning