Edge Intelligence Unleashed: Mastering Embedded AI for Industry Advancement
This 3-day winter school offers a unique platform for AI professionals to learn about the latest developments in embedded AI and its applications, by alternating theoretical sessions and hands-on experiments.
Practical information:
Want to register?
- Register until: 21 Jan 2026
- Prerequisites: basic notions of data structures and algorithms, signal processing, convolutional neural networks and languages C++, Python & Linux (command line instructions)
- Price: € 1200
Georganiseerd door:
Artificial intelligence is gradually becoming an integral part of production chains and business processes. In recent years, more and more AI tasks are being performed at the device level rather than on powerful cloud servers. Embedded AI offers numerous benefits and can be used for a multitude of tasks (such as process automation, improving customer service, advanced analytics, etc.), resulting in an exponential growth in the number of use cases.
During this exclusive winter school, we will examine in detail how machine and deep learning can be applied at the device level. Which components and frameworks are needed for edge processing? Both hardware and software will be covered, as well as techniques for optimizing network architectures. In addition, there is plenty of room to experiment under the guidance of experts and to bridge the gap to your own business case. After the three-day programme, you will have a solid theoretical foundation regarding embedded AI, supplemented with practical tools to use in your own work context through the hands-on approach of the training.
Date and location
- KU Leuven Campus De Nayer (Jan de Nayerlaan 5, 2860 Sint-Katelijne-Waver)
- 28, 29 and 30 January 2026
- Day programme:
- 8.30h - 9h: welcome coffee
- 9-12.30h: morning session
- 12.30-13h: lunch
- 13h - 16.30h: afternoon session
- 16.30 - 17.30h: closing reception (only on Wednesday)
Target Audience
The target audience for this training is professionals and experts interested in applying machine learning and deep learning to embedded systems in their respective industries. This may include hardware and software engineers, data scientists, machine learning engineers, embedded system designers, functional analysts, R&D managers and researchers working in fields such as computer vision, natural language processing, robotics, and IoT. The training is designed for individuals who already have a basic understanding of machine learning and deep learning and are looking to expand their knowledge and skills in applying these techniques to embedded systems.
Basic notions of data structures and algorithms, signal processing, convolutional neural networks and languages C++, Python & Linux (command line instructions) are needed to follow the programme adequately.
Goals
- Gain a comprehensive understanding of machine and deep learning and their applications in embedded systems.
- Learn about the necessary components and frameworks for edge processing and how to optimize network architectures.
- Understand the hardware and software required for embedded AI, and the different techniques available for optimizing embedded machine learning algorithms.
- Develop practical skills using tools, such as Edge Impulse and TensorFlow Lite for implementing embedded AI.
- Learn how to apply embedded AI to real-world business cases, and how to bridge the gap between theory and practice.
- Understand the potential benefits and limitations of embedded AI, and how to evaluate the suitability of different techniques for specific use cases.
Program
28 January 2026
Session 1: Introduction
Lecturer: Prof. Mathias Verbeke
Setting the context for the rest of the winter school:
- Introduction to machine learning & deep learning
- Embedded machine learning
- Use cases and company pitches
Session 2: Workshop “Edge Impulse”
Lecturer: Dr. Jonas Lannoo
In this workshop, we use “Edge Impulse”, the online edge AI platform: a low-code environment to develop, train and deploy AI models on edge devices. It is widely applicable to quickly train a neural network and place the result on a microcontroller or any other edge device. With a simple but intuitive example, we discover the broad possibilities of this powerful software tool and create our first functional edge-deployed AI model.
29 January 2026
Session 3 and 4: TinyML (running ML models on microcontrollers)
Lecturers: Prof. Toon Goedemé & Prof. Peter Karsmakers
Theory: TinyML design flow for inference:
- Model compression: hardware-friendly model architectures, quantisation, pruning, knowledge distillation
- Model optimization for edge hardware
- Model deployment
Workshop: Compress and optimize a computer vision application for deployment on a microcontroller. Design validation using an ESP-EYE microcontroller.
30 January 2026
Session 5: Workshop FPGA
Lecturer: Wouter Hellemans
In this session, we will establish the landscape of ML on Field Programmable Gate Arrays (FPGAs) and investigate how CNNs can be accelerated on FPGAs for high-throughput applications. Specifically, we will explore a network security case by developing a CNN-based intrusion detection system. During the session, we will make use of the open-source libraries Brevitas and FINN to quantize our model and convert it to specialized hardware.
Session 6: Distributed AI
Lecturer: Prof. dr. Hans Hallez
Focus on distributed working with artificial intelligence:
- How can AI algorithms be scaled and distributed over a network of systems?
- Deep dive into concepts like Edge Computing, Big Data, Machine Learning
There will be ample time to wrap up the winter school with lessons learned and a closing drink.
Teachers / speakers
Toon Goedemé studied electrical engineering at KU Leuven. He received the Ph.D. degree in vision-based topological navigation from KU Leuven, in December 2006, under the guidance of Prof. L. Van Gool and T. Tuytelaars. Afterwards, he started teaching at the Technical University De Nayer, Sint-Katelijne-Waver, where he founded his research group Embedded and Artificially Intelligent Vision Engineering (EAVISE), in 2008. Nowadays, his group is integrated in the KU Leuven and consists of three professors (Joost Vennekens, Patrick Vandewalle, and himself), four postdocs and about 20 researchers, playing a vital role in the transfer of computer vision and AI know-how from academic research towards the industry. Since 2014, he has been an Associate Professor with KU Leuven. He is the (co)author of more than 190 international publications and was a project leader of more than 75 industrially co-founded research projects. Together with his team, he won several awards, such as the Best Paper Award at Embedded Vision Workshop CVPR 2015, the Best Demo Award at BNAIC 2015, the Best Paper Award at CGVCVIP 2016, the Willy Asselman Award for research achievements in 2016, and the Best Paper Award at Embedded Vision Workshop ECCV 2020. He is also an Associate Editor of the IET Computer Vision journal and the MDPI Journal of Imaging.
Hans Hallez is a lecturer (Docent) of physics and informatics to 1st year (freshmen) academic bachelor Industrial Engineering students. This is within the faculty of Industrial Engineering (FIIW) of the KU Leuven (TechnologyCampus Oostende). In the final master year, he also teaches "optoelectronic communication" to electronic engineering students.
His research interests are within electronic implementation for medical and industrial applications. More specifically his interest lies in the implementation of signal-processing algorithms within programmable wireless sensor networks. He is also interested in new sensors and measurement techniques.
Hallez is proficient in conducting research concerning electronics, physics and ICT with medical applications. From the more fundamental research on EEG and ECG signal processing at the UGent, he's gone to research on a demand-driven and practical basis at KU Leuven. There he is responsible for teaching and conducting research.
onderzoeker bij COSIC (KU Leuven)
Peter Karsmakers
Dr. Peter Karsmakers received the M.Sc. degree in artificial intelligence in 2004 and the PhD degree from the Department of Electrical Engineering, KU Leuven, in 2010. From 2010 to 2013, he was a post-doctoral researcher in the MOBILAB research team from Thomas More. From 2013 to 2018, he worked as a post-doctoral researcher at KU Leuven where he co-founded the ADVISE research team. Currently, he is an Associate Professor within the Computer Science Department in the DTAI section at KU Leuven and is a member of the Leuven.AI institute. Since 2022, he is a PI of Flanders Make@KU Leuven. His research interests include designing machine learning algorithms that consider application-specific constraints. These can, for example, relate to the computing platform on which the machine learning algorithm will be deployed on, to the need of physical consistency between model variables, to the lack of data annotation or to other application related specifications. He worked on diverse projects, mostly in collaboration with industrial partners, that involve monitoring of both humans as machines using sensors such as microphones, accelerometers and radars.
Jonas Lannoo
PhD, Innovation Manager Mechatronics at University College VIVES, Senior Researcher in research group IoT, Mechatronics and Robotics, TinyML Teacher and Researcher, Bruges.
Assistant Professor at KU Leuven, Declaratieve Talen en Artificiële Intelligentie (DTAI)
