Skip to main content
Go to the home page of the European Commission (opens in new window)
English en
CORDIS - EU research results
CORDIS

Faster and More Energy Efficient Machine Learning for Embedded Systems

Project description

Expediating and improving artificial intelligence system development

Artificial intelligence (AI) and machine learning technologies have the potential to provide significant benefits across various sectors and processes. Many organisations, corporations, and entities are actively engaged in research and development to create innovative tools and software based on these technologies. However, AI development, particularly in deep learning (DL), can be challenging and time-consuming, resulting in many projects remaining incomplete. The EU-funded EmbeDL project aims to address this issue by developing a revolutionary software development kit for on-premises installation. This kit not only optimises complex DL models on hardware systems but also provides manufacturers with essential toolchains and services. These services are designed to enhance the quality and efficiency of development, ultimately reducing the time required for completion.

Objective

EmbeDL is a Software Development Kit installed on premises to optimise complex DL models on embedded hardware systems. It empowers product manufacturers by providing them with the entire toolchain and services necessary to accelerate their AI-driven system development and launch into production. What is currently taking months, years or abandoned R&D, can now be done in weeks. Using the EmbeDL platform, the product development team can:
-Automatically optimise a DL model for specific hardware while meeting energy consumption, hardware cost, and other requirements, by pruning/compressing a state of the art model in a hardware and requirements-aware fashion or searching automatically for the optimal model.
-Automatically evaluate hardware for its model (currently existing as an internal tool to be developed into a full fledged product), by a combination of predictive methods and hardware-in-the-loop.
-Accelerate the development cycle with easy to use and highly automated tools.

Fields of science (EuroSciVoc)

Keywords

Programme(s)

Topic(s)

Funding Scheme

HORIZON-EIC-ACC-BF - HORIZON EIC Accelerator Blended Finance

See all projects funded under this funding scheme

Call for proposal

(opens in new window) HORIZON-EIC-2022-ACCELERATOR-01

See all projects funded under this call

Coordinator

EMBEDL AB
Net EU contribution
€ 2 499 999,00
Address
GAMLA ALMEDALSVAGEN 39 PLAN 3
412 63 Goteborg
Sweden
SME
Yes
Region
Södra Sverige Västsverige Västra Götalands län
Activity type
Private for-profit entities (excluding Higher or Secondary Education Establishments)
Links
Total cost
€ 3 640 830,00