Track / Overview

Edge AI means that artificial intelligence algorithms process data locally on a hardware device. The algorithms use sensor data, such as an image, vibrations or audio, which is created in the device sensors. An Edge AI device can process data and make decisions without any connection. The edge device can be a mobile phone, microcontroller or a single board computer. 

The tiny ML detection algorithms are getting better, and we can fit them on a microcontroller. The latest development in low-power microcontrollers enables us to build an IoT device which can run for a long time with just a small battery, while continuously analysing sensor data with artificial intelligence algorithms. 
What are the latest research topics and directions in tiny ML algorithms? The Edge AI solution development platforms have taken a major step, we can now build solutions for a microcontroller more easily. 
What do these platforms offer? 
What are the latest hardwares and what kind of Edge AI solutions are possible to build in practice? 
How to build a complete Edge AI IoT Solution? 
What kind of needs exists on the customer side for Edge AI IoT?

New mobile phones have hardware accelerated units which enables us to run complex algorithms with large input size. This development brings new opportunities for mobile app developers to build rich mobile applications. 
How can we use these different types of hardware acceleration and get the most out of it? 
How can we handle the large performance diversity of mobile phones on the application level? 
What are the best product ideas to use these new technology opportunities?

Single board computers have found their place among Edge AI devices where high processing power is needed. What are the latest boards and hottest applications? These boards have often been used in PoC, but how to build a single board computer Edge AI solution as a real product?

Track / Schedule


With Henrik Karppinen

Building Blocks and Manual for the Edge AI of Tomorrow

With Niko Vuokko

Energy-Efficient Tiny Machine Learning at the Edge for Next Generation of Smart Sensors

With Michele Magno


Making the Impossible, Possible

With Aurelien Lequertier

Machine Health Monitoring Using Acoustic Sensing at the Edge

With Jon Nordby

Efficient Computer Vision on Edge Devices: How we Guide Blind People Using Python

With Bruno Vollmer

Leveraging Synthetic Data for Mobile Object Detection

With Vidit Vidit

Object Detection on Mobile using YoloV5

With Jeanne Fleury

Track / Speakers

Henrik Karppinen

Edge AI Tech Lead, SBB

Jeanne Fleury

BizDevOps Engineer, SBB

Michele Magno


Aurelien Lequertier

VP of Solutions Engineering, Edge Impulse

Jon Nordby

Head of Machine Learning, Soundsensing

Vidit Vidit

PhD Student, EPFL

Niko Vuokko

Head of Technology, Silo AI

Bruno Vollmer

CTO, biped

Track / Co-organizers

Henrik Karppinen

Edge AI Tech Lead, SBB

Jeanne Fleury

BizDevOps Engineer, SBB

AMLD EPFL 2022 / Tracks & talks

AMLD Keynote Session – Monday morning

Marcel Salathé, Lenka Zdeborová, Carmela Troncoso, Chiara Enderle, Patrick Barbey, Thomas Wolf, Gunther Jansen, Laure Willemin, Simon Hefti, Arthur Gassner

10:00-12:00 March 28Auditorium A

AI & Physics

Francesca Mignacco, Gert-Jan Both, Michael Unser, Thomas Asikis, Dalila Salamani, Pietro Rotondo, Tom Beucler, Giulio Biroli

12:30-18:00 March 285BC

AI & Pharma

Asif Jan, Jonas Richiardi, Patrick Schwab, Naghmeh Ghazaleh, Alexander Büsser, Carlos Ciller, Caibin Sheng, Silvia Zaoli, Félix Balazard, Giulia Capestro, Marianna Rapsomaniki, Martijn van Attekum

13:30-17:30 March 281BC

AMLD / Global partners