Join this unique platform for AI-professionals to gain knowledge about the latest developments in embedded AI and its applications, by alternating theoretical sessions and hands-on experiments

Embedded AI for Industry

6 Sep 2023 - 8 Sep 2023

During this exclusive summer 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 program, you will have a solid theoretical foundation

More info & registration ⇗

Practical information:

6 Sep 2023 - 8 Sep 2023

Spoorwegstraat 12, 8200 Brugge

English

Target audience: professionals and experts interested in applying machine learning and deep learning to embedded systems

Want to register?

Prerequisites: 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.
Price: 1800

More info & registration ⇗

Georganiseerd door:

6 September 2023

Session 1: Introduction

Lecturer: Prof. Mathias Verbeke

Setting the context for the rest of the summer school:

- Introduction to machine learning & deep learning

- Embedded machine learning

- Use cases and company pitches

Session 2: Workshop “Edge Impulse”

Lecturer: Dr. Jonas Lannoo

Work on a use case using “Edge Impulse”: a tool requiring little to no programming experience. It is widely applicable to quickly train a neural network and place the result on a microcontroller or edge device. In this example, written letters or characters will be distinguished using a trained network, with the help of a microcontroller with an accelerometer attached to a pen.

7 September 2023

Session 3 and 4:

Lecturers: Prof. Toon Goedemé & Prof. Peter Karsmakers

Theory that is on the programme during the second day:

- How to optimize convolutional neural networks, in order to execute them on small embedded edge platforms

- Weight & activation quantisation

- Layer fusion

- Pruning

- Hardware-friendly neural networks

Workshop: Tensorflow Lite

Optimize a computer vision application using Tensorflow Lite. Learn how to implement this on an ESP-EYE microcontroller.

8 September 2023

Session 5: Workshop FPGA

Lecturers: Laurens Lejeune & Wouter Hellemans

How can neural networks be used on Field-Programmable Gate Arrays? Some open source libraries are offered to facilitate the translation from neural network to hardware. We try to accelerate the CNNs used for network security on FPGA.

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 summer school with lessons learned and a closing drink.