SubsidieMeestersFaster and More Energy Efficient Machine Learning for Embedded Systems
EmbeDL is a software toolkit that accelerates the optimization of deep learning models for embedded systems, reducing development time from months to weeks while meeting specific hardware requirements.
Projectdetails
Introduction
EmbeDL is a Software Development Kit installed on premises to optimize 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.
Features
Using the EmbeDL platform, the product development team can:
-
Automatically optimize 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.
Financiële details & Tijdlijn
Financiële details
| Subsidiebedrag | € 2.499.999 |
| Totale projectbegroting | € 3.640.830 |
Tijdlijn
| Startdatum | 1-4-2023 |
| Einddatum | 30-9-2025 |
| Subsidiejaar | 2023 |
Partners & Locaties
Projectpartners
- EMBEDL ABpenvoerder
Land(en)
Vergelijkbare projecten binnen EIC Accelerator
| Project | Regeling | Bedrag | Jaar | Actie |
|---|---|---|---|---|
Optimisation of a novel software tool for automation of the design & verification process of semiconductor developmentLUBIS EDA is developing software to automate chip design and verification, ensuring error-free production, faster market entry, and increased revenue for semiconductor developers. | EIC Accelerator | € 2.499.999 | 2024 | Details |
A novel hardware & software platform to revolutionise artificial intelligence at the edgeDeveloping a scalable hardware and software platform for efficient edge AI inference, targeting computer vision and NLP, to drive adoption with reduced costs and power consumption. | EIC Accelerator | € 2.499.999 | 2024 | Details |
Scalable Unified Processor Enhancing Revolutionary Computing, Harnessing Integrated Performance for Edge AI, Autonomous Driving, Generative AI, and Decentralized AIoT ApplicationsDeveloping the Tyr chip to enable real-time, efficient processing for Level 4/5 autonomous driving, addressing current data and processing limitations in the industry. | EIC Accelerator | € 2.499.999 | 2023 | Details |
End to end Real-time Interactive Edge AI analytics platform for Industry and AutomotiveDeveloping an end-to-end edge AI platform for Industry and Automotive, enabling non-coders to create real-time AI models efficiently for faster market deployment. | EIC Accelerator | € 2.499.999 | 2022 | Details |
Optimisation of a novel software tool for automation of the design & verification process of semiconductor development
LUBIS EDA is developing software to automate chip design and verification, ensuring error-free production, faster market entry, and increased revenue for semiconductor developers.
A novel hardware & software platform to revolutionise artificial intelligence at the edge
Developing a scalable hardware and software platform for efficient edge AI inference, targeting computer vision and NLP, to drive adoption with reduced costs and power consumption.
Scalable Unified Processor Enhancing Revolutionary Computing, Harnessing Integrated Performance for Edge AI, Autonomous Driving, Generative AI, and Decentralized AIoT Applications
Developing the Tyr chip to enable real-time, efficient processing for Level 4/5 autonomous driving, addressing current data and processing limitations in the industry.
End to end Real-time Interactive Edge AI analytics platform for Industry and Automotive
Developing an end-to-end edge AI platform for Industry and Automotive, enabling non-coders to create real-time AI models efficiently for faster market deployment.
Vergelijkbare projecten uit andere regelingen
| Project | Regeling | Bedrag | Jaar | Actie |
|---|---|---|---|---|
Enabling Homomorphic Encryption of Deep Neural Network Models and Datasets in Production EnvironmentsHomE aims to revolutionize encrypted deep learning by leveraging persistent memory technology to enhance performance and enable large model execution beyond current DRAM limitations. | ERC Consolid... | € 2.680.195 | 2022 | Details |
Outplaying the hardware lottery for embedded AIThe BINGO project aims to revolutionize embedded AI by enabling rapid customization of heterogeneous compute platforms using prefabricated chiplets, achieving 100x efficiency gains in days. | ERC Consolid... | € 1.995.750 | 2023 | Details |
Algorithmic Bias Control in Deep learningThe project aims to develop a theory of algorithmic bias in deep learning to improve training efficiency and generalization performance for real-world applications. | ERC Starting... | € 1.500.000 | 2022 | Details |
Reconciling Classical and Modern (Deep) Machine Learning for Real-World ApplicationsAPHELEIA aims to create robust, interpretable, and efficient machine learning models that require less data by integrating classical methods with modern deep learning, fostering interdisciplinary collaboration. | ERC Consolid... | € 1.999.375 | 2023 | Details |
ANalogue In-Memory computing with Advanced device TEchnologyThe project aims to develop closed-loop in-memory computing (CL-IMC) technology to significantly reduce energy consumption in data processing while maintaining high computational efficiency. | ERC Advanced... | € 2.498.868 | 2023 | Details |
Enabling Homomorphic Encryption of Deep Neural Network Models and Datasets in Production Environments
HomE aims to revolutionize encrypted deep learning by leveraging persistent memory technology to enhance performance and enable large model execution beyond current DRAM limitations.
Outplaying the hardware lottery for embedded AI
The BINGO project aims to revolutionize embedded AI by enabling rapid customization of heterogeneous compute platforms using prefabricated chiplets, achieving 100x efficiency gains in days.
Algorithmic Bias Control in Deep learning
The project aims to develop a theory of algorithmic bias in deep learning to improve training efficiency and generalization performance for real-world applications.
Reconciling Classical and Modern (Deep) Machine Learning for Real-World Applications
APHELEIA aims to create robust, interpretable, and efficient machine learning models that require less data by integrating classical methods with modern deep learning, fostering interdisciplinary collaboration.
ANalogue In-Memory computing with Advanced device TEchnology
The project aims to develop closed-loop in-memory computing (CL-IMC) technology to significantly reduce energy consumption in data processing while maintaining high computational efficiency.