CIS Edge AI Summer School: 3 days to explore the potential of Edge AI
© 2022 CIS edge AI Summer School 2022 | Alain Herzog
From June 13-15, the Center for Intelligent Systems (CIS) welcomed 95 selected participants from around the world to attend the CIS Edge AI Summer School 2022. During these three days, attendees learned about designing Edge AI algorithms, systems, and applications from some of the world-renowned experts in the field.
As our devices and lives are getting more and more connected, the Internet of Things (IoT) is now a key part of our lives and so is Edge AI technology.
Edge AI is the processing of Artificial Intelligence algorithms on edge, that is, on users’ devices. The concept derives from Edge Computing, which starts from the same premise: data is stored, processed, and managed directly on the devices used by users in comparison to Cloud Computing where the data is processed and stored using data centers and accessed over the internet.
Edge AI is still a relatively new field, yet it is rapidly expanding, and offering strong promise for example for data privacy and efficiency. Consumer devices, such as smartphones and wearables now account for the majority of edge AI use cases. However, with the expansion of smart cities, medicine and more and more connected objects the importance of edge AI technology is expected to grow.
Integrating various domains from engineering to sensors to algortithms the CIS promotes and supports several edge AI projects as part of its research pillars and the Digipredict initative.
This summer, the CIS welcomed 95 selected participants from around the world to the first CIS Edge AI Summer School from June 13-15 to discuss the state of the art of edge AI. The event was rich in presentations on the topic covering efficiency and performance aspects, co-design of algorithms and hardware, as well as robustness, sustainability and ethics. In addition to the keynotes, the event allowed all participants to present their work during poster sessions allowing them to connect and discuss their research.
Day 1 - Edge AI Algorithms
The first day featured a deep dive on the topic of edge AI Algorithms. The summer school kicked off with a keynote on Federated Learning at Scale from Prof. Mike Rabbat, Research Scientist & Manager, Meta AI - FAIR
The second part of the day, Prof. Dimitris Papailiopoulos, Assistant Professor of Electrical and Computer Engineering and Computer Sciences, University of Wisconsin-Madison walked us through his presentation “Model Pruning and the Hunt for Lottery Tickets”
To close this first day both speakers were reunited on stage for a panel discussion on Edge AI Algorithms moderated by Dr. Tao Lin, EPFL and Westlake University.
Day 2 - Embedded AI Architectures
The second day addressed the theme of Embedded AI architecture. Prof. Davide Rossi, Associate Professor, Department of Electrical, Electronic, and Information Engineering University Of Bologna opened this second day with his presentation “PULP: Embedding AI at the Extreme Edge of the IoT”
Followed by Prof. Mohammad Abdullah Al Faruque from University of California, Irvine who gave a keynote entitled “Design Methodologies for Flexible, Robust, and Energy-Efficient Edge AI
To end the second day, a panel discussion between Prof. Mohammad Abdullah Al Faruque, Prof. Davide Rossi and Prof. David Atienza moderated by Dr. Giovanni Ansaloni, both from EPFL, led to an insightful conversation on Embedded AI architecture.
Day 3 - Edge AI Applications
On the last day, edge AI applications including ethical aspects were discussed. Prof. Onur Mutlu, Professor of Computer Science, Department of Information Technology and Electrical Engineering, ETH Zurich and Adjunct Professor at Carnegie Mellon University dived right in with his talk on “Memory-Centric Computing".
The second presentation was given by Prof. Subhasish Mitra, Department of EE and Department of CS, Stanford University who presented his work on “The Future of Hardware Technologies for Computing N3XT 3D MOSAIC, Illusion Scaleup, Co-design”
The final talk of the summer school was given by Prof. François Terrier, Director of Research, AI program VP, CEA, Professor at the National Institute of Nuclear Science and Technologies (INSTN) who talked about AI from research to industry as well as its potential for Industry & Society.
To close the day and the event a panel discussion on edge AI applications took place between Prof. Subhasish Mitra, Prof. François Terrier and Prof. Adrian M. Ionescu moderated by Dr. Nataliya Yakymets, both EPFL.
The CIS thanks all the participants as well as the speakers and organizing committee: Giovanni Ansaloni , David Atienza Alonso, Mihai Adrian Ionescu, Martin Jaggi, Jan Kerschgens, James Larus, Tao Lin and Nataliya Yakymets.
Photo gallery: Here
About Center for Intelligent Systems
EPFL launched the Center for Intelligent Systems (EPFL CIS) in October 2019. This center is a joint initiative of the schools ENAC, IC, SB,STI and SV that integrates research in Artificial Intelligence (AI), Machine Learning (ML) and Robotics to foster integrative research streams leading to the development of Intelligent Systems. Intelligent Systems perceive their environment, can learn from the data they collect and adapt to the changing world around them. Intelligent Systems can take many forms. When available, such systems will have profound implications for many areas including manufacturing, transportation, commerce, employment, healthcare, government, legal, security, privacy, and education.
Four integrative research pillars have already been launched since the inception of CIS: "AI for Medicine", "Intelligent Assistive Robotics", "Decentralized edge AI Infrastructure" and "Digital Twin". Furthermore, the EPFL Center for Intelligent Systems supports its 70 associated professors in their teaching and training mission of future engineers/scientists. In addition, the EPFL CIS serves as a "one-stop-shop" for questions from industry, society and politics on the topics of artificial intelligence, machine learning and robotics and pro-actively promotes technology transfer from research to society and industry by organizing thematic conferences such as the EPFL Digital Twin Days in November 2021. Finally, through its work and contacts, the CIS integrates EPFL into European and international research and excellence networks.
Sign up for the Center for Intelligent Systems (CIS) newsletter to stay up to date with the CIS’ activities, events and opportunities. Subscribe