Periodic Reporting for period 2 - EmbeDL (Faster and More Energy Efficient Machine Learning for Embedded Systems)
Periodo di rendicontazione: 2024-04-01 al 2025-09-30
Embedl’s EIC Accelerator aims at scaling its advanced AI technology business. This is done by streamlining development and sales for scaleability, continuously developing and improving the world-leading model optimization SDK product, and broadening its product portfolio with additional products. Significant efforts to reach a global market and position Embedl as a leader in edge AI is also included.
Project Context
The current state-of-the-art deep learning optimization on embedded systems relies on deep learning experts. However, they are highly sought after, and expensive, and manual optimization is time-consuming and not scalable. In addition, hardware updates or deep learning model updates (device functionality updates) are very frequent. The result is that manual optimization must be conducted again from scratch. This makes this endeavor highly unsustainable.
Objectives
Embedl automatically compresses and optimises DL models for specific hardware. The benefits for users are
clear:
→Significantly reduced optimisation time (thus reducing cost and reducing the resources needed)
→Increased performances of the device (larger DL model run on the same device), up to 1000% increase in
execution time
→Decrease energy consumption of the device (up to 90%)
→Potential for significant cost savings by using cheaper hardware to run the same DL model (up to 44% cost reduction in
hardware price).
Pathway, how, plan
The technical work packages in the project are focusing on four major areas:
Improve software development infrastructure to scale with more customers, more developers and more products.
Technical advances in the product portfolio.
How the results are expected to contribute
Strengthening our product offering and our ability to support many more customers and more diverse customers will contribute to our capability of becoming a world leader supplier in embedded AI development tools.
Project Context
The current state-of-the-art deep learning optimization on embedded systems relies on deep learning experts. However, they are highly sought after, and expensive, and manual optimization is time-consuming and not scalable. In addition, hardware updates or deep learning model updates (device functionality updates) are very frequent. The result is that manual optimization must be conducted again from scratch. This makes this endeavor highly unsustainable.
Objectives
Embedl automatically compresses and optimises DL models for specific hardware. The benefits for users are
clear:
→Significantly reduced optimisation time (thus reducing cost and reducing the resources needed)
→Increased performances of the device (larger DL model run on the same device), up to 1000% increase in
execution time
→Decrease energy consumption of the device (up to 90%)
→Potential for significant cost savings by using cheaper hardware to run the same DL model (up to 44% cost reduction in
hardware price).
Pathway, how, plan
The technical work packages in the project are focusing on four major areas:
Improve software development infrastructure to scale with more customers, more developers and more products.
Technical advances in the product portfolio.
How the results are expected to contribute
Strengthening our product offering and our ability to support many more customers and more diverse customers will contribute to our capability of becoming a world leader supplier in embedded AI development tools.
We have improved the scalability of our software development infrastructure and implemented several security policies.
Our flagship product, the Model Optimization SDK, has been significantly improved and extended with Neural Architecture Search and Advanced Quantization support. The supported hardware platforms have been extended from four to ten. We have successfully carried out market verification pilots with very reputable customers in the automotive and defense space.
We have launched a SaaS offering, the Embedl Hub, to drive market recognition and leads to our Model Optimization SDK. In 2026 we will introduce a paid tier, so the platform will also be a source of revenue by itself going forward.
Our flagship product, the Model Optimization SDK, has been significantly improved and extended with Neural Architecture Search and Advanced Quantization support. The supported hardware platforms have been extended from four to ten. We have successfully carried out market verification pilots with very reputable customers in the automotive and defense space.
We have launched a SaaS offering, the Embedl Hub, to drive market recognition and leads to our Model Optimization SDK. In 2026 we will introduce a paid tier, so the platform will also be a source of revenue by itself going forward.
Technically, we have further advanced our already state-of-the-art optimization engine and applied for six patents during the project.
We have maintained significant communication with investors throughout the project and secured a € 5.5 million pre-series A funding round in Q2 2025, which will secure the company's financial stability after the project concludes.
To increase market awareness, we have been actively present at trade shows and conferences, where we have presented on stage, hosted a booth, and/or visited and networked in Europe and the US. We have also significantly increased our online visibility with blog posts, webinars, LinkedIn posts, and online advertising.
We have maintained significant communication with investors throughout the project and secured a € 5.5 million pre-series A funding round in Q2 2025, which will secure the company's financial stability after the project concludes.
To increase market awareness, we have been actively present at trade shows and conferences, where we have presented on stage, hosted a booth, and/or visited and networked in Europe and the US. We have also significantly increased our online visibility with blog posts, webinars, LinkedIn posts, and online advertising.