The KIOS Research and Innovation Center of Excellence at the University of Cyprus is co-organizing the inaugural tinyML EMEA Technical Forum, which will be held online between the 7th to 10th of June 2021. The forum follows the unprecedented success of the tinyML Summit that was organized during the last three years in Silicon Valley (with over 5000 registered participants from industry, academia and governmental and policy making organizations) and aims to expand in the EMEA region, with speakers and participants showcasing technology from Europe, Middle East, and Africa (EMEA). The current plan is for Cyprus to host the first physical event in the summer of 2022.

 

tinyML is a fast growing branch of machine learning technologies, architectures and approaches dealing with machine intelligence at the very edge. It is broadly defined as integrated, “full-stack” (HW-SYS-SW-apps), ML architectures, techniques, tools and approaches capable of performing on-device analytics for a variety of sensing modalities (vision, audio, motion, environmental, human health monitoring etc.) at extreme energy efficiency, typically in the single mW (and below) power range, enabling machine intelligence right at the boundary of the physical and digital worlds.

 

The tinyML Technical Forum features an exciting blend of tutorials, keynote talks, panels, industry and policy-maker perspectives, and a student research forum, addressing an abundance of topics.

 

Tutorials:
There are two tutorials open to the attendees on Monday, June 7th:

Bio-inspired neuromorphic circuits architectures
Presented by Giacomo Indiveri, Professor, Institute of Neuroinformatics, University of Zurich and ETH Zurich.

Context Awareness Function Pack (FP)
Presented by ST Microelectronics - This live tutorial will feature experts from ST Microelectronics covering the joint use of STM32 and In-sensor computing with machine learning core.

Keynote Talks and Abstracts:
• Bottom-up and top-down neural processing systems design: unveiling the road toward neuromorphic intelligence
Charlotte Frenkel, Postdoctoral Researcher, Institute of Neuroinformatics

 

While Moore’s law has driven exponential computing power expectations, its nearing end calls for new roads to embedded cognition. In this talk we will show how to best exploit a bottom-up (neuroscience-driven) approach and a top-down (application-driven) one toward embedded cognition and neuromorphic intelligence.

______________________________________________________________________________________________________________________________________________________

tinyML Beyond Audio and Vision
Wolfgang Furtner, Distinguished Engineer for System Architecture, Infineon

 

This talk introduces you to a few sensors beyond microphones and cameras and to what embedded ML applications are interesting for these sensors and will conclude with an outlook on future embedded hardware and software.

_____________________________________________________________________________________________________________________________________________________

The model efficiency pipeline, enabling deep learning inference at the edge
Bert Moons, Research Scientist, Qualcomm

 

A model-efficiency pipeline achieves this goal: automatically optimizing deep learning applications through Hardware-Aware Neural Architecture Search, compressing and pruning redundant layers and subsequently converting them to low-bitwidth integer representations with state-of-the-art data-free and training-based quantization tools.

______________________________________________________________________________________________________________________________________________________

A novel approach to building exceptionally tiny, predictive and explainable models for non-data scientists
Blair Newman, CTO, Neuton

 

Performing compute and inference on the edge solves most issues with privacy, latency and reliability, but how do we address the remaining obstacles?

______________________________________________________________________________________________________________________________________________________

Shaping the digital future of Europe
Colette Maloney, Head of Unit “Microelectronics and Photonics Industry”, European Commission - DG Communications Networks, Content and Technology

 

This presentation will discuss a number of new strategic initiatives that the European Commission has put forward in digital technologies with the ambition to shape our digital future and foster European competitiveness.

_____________________________________________________________________________________________________________________________________________________

 

Please view the schedule for abstracts and bios.

 

The entire event is free of charge thanks to the Forum’s Sponsors -- Neuton, Arm, Edge Impulse, Qualcomm, Infineon, and Seeed.


The forum also features contributions from the EMEA Industry and Academia, and hosts a Student Research Forum, that showcases research activities from across the EMEA Region. Further, the forum features a cross-pollinating session on June 10th, between various EMEA stakeholders, that aims to boost the tinyML growth in the EMEA region featuring a multi-disciplinary panel, highlights of success stories, and reviews of networking activities and initiatives that take place in the EMEA region!

 

For free registration and more information about the forum, please visit: https://www.tinyml.org/event/emea-2021/

 

The KIOS CoE welcomes everyone who is interested in machine learning technologies to participate in this major event!