2
0
2
0

EPFL new Center for Intelligent Systems

Read article
Physics
robotics
artificial intelligence
computer science
covid-19
digital
data

Publicly announced in May 2020, EPFL’s new Center for Intelligent Systems (CIS) acts as a research promotion platform bringing together experts in machine learning, data science, computer vision, cyberphysical systems, and robotics.

Initially conceived to unite the School of Architecture, Civil and Environmental Engineering (ENAC), Engineering (STI), Computer and Communication Sciences (IC) and Basic Sciences (SB), CIS’s unique mission is to connect and support all EPFL researchers working in fields related to intelligent systems. These fields are developing technologies that, when brought together, can be used to construct intelligent systems capable of making complex, nuanced decisions in challenging, dynamic environments.

CIS Executive Director Jan Kerschgens says his goal for the center is to get researchers out of their research silos and comfort zones to pursue ambitious and collaborative projects, “we have never had four schools come together like this to promote research and technology transfer under the umbrella of intelligent systems. The CIS is also 100% synergistic with other EPFL centers like the Center for Digital Trust and the Swiss Data Science Center.”

In order to support its mission, the CIS has put several key activities in place.

Learn about colleagues’ research and interests

With the support of the CIS Scientific Committee, a colloquium series brings together and invites professors and researchers from EPFL and around the world, working on different aspects of Intelligent Systems, to discuss the current state of the art. Guests have already included well-known professors Shafi Goldwasser (MIT), Radhika Nagpal (Harvard, Wyss Institute) and Bin Yu (UC Berkeley).

Kerschgens has also overseen the launch of the “Get to Know your Neighbor” seminar series that offers a platform for the EPFL community and its professors to present and learn about their colleagues’ research and interests.

To further encourage research in the vast field of intelligent systems, in July 2020 the center launched the CIS Collaboration Grant program. So far, three grants have been attributed, each corresponding to different research pillars: AI Healthcare, Intelligent Assistive Robotics, and Edge AI. In line with the center’s collaborative mindset, each project is developed between at least two EPFL Labs.

International project

The CIS has also organized and hosted workshops with professors and postdocs. One of the first results of these exchanges is the granting of the FET-Proactive “DIGIPREDICT” by the European Commission. This interdisciplinary project aims to develop a technology, based on artificial intelligence, capable of predicting serious cardiovascular dysfunctions due to coronavirus and, in the longer term, inflammatory diseases. It is a collaboration between Adrian Ionescu’s Nanoelectronic Devices Laboratory, David Atienza’s Embedded Systems Laboratory, Kamiar Aminian’s Motion Measurement and Analysis Laboratory and Martin Jaggi’s Machine Learning and Optimization Laboratory as well as a dozen European partners including universities, hospitals and start-ups.

“We are proud to be supporting our first international project, DIGIPREDICT, that combines transversal axes of research in intelligent systems and that values the linkage of internal and external partners at EPFL. We will be in charge of promoting the program and disseminating its results, » says Kerschgens.

The CIS also hosts the EPFL ELLIS unit, part of the ELLIS society, a pan-European initiative aimed at bringing together experts in machine learning and intelligent systems. Currently, there are 30 sister units across Europe.

Collaborative research

Finally, CIS acts as a point of contact with industry, as well as Swiss and international stakeholders, to create long-term partnerships and accelerate innovation in complex systems. As Ali H. Sayed, Dean of EPFL’s School of Engineering says, “we are at a crossroads, moving from the intelligent design of systems towards the design of intelligent systems. These will contribute to science, education, industry, and the economy at large. They will enable scientists and engineers to explore complexity and the design space more fully. Through CIS, EPFL is positioning itself to lead in this domain.”

 

«We want to have an impact, on COVID-19 research for example, as a benefit of having experts working together.»

The CIS launched with the onset of the coronavirus pandemic and its members are already leveraging the new resource to brainstorm collaborative research projects, notably in the areas of health and medicine. “We want to have an impact, on COVID-19 research for example, as a benefit of having experts working together,” IC Dean James Larus told attendees at the first CIS seminar on April 6th 2020.

Indeed, STI professor and CIS Scientific Committee member David Atienza this year announced the development of the Coughvid app in his Embedded Systems Lab (ESL), in collaboration with students from STI, IC, and SB. The concept for the app? It listens to your cough and use AI to predict whether you have coronavirus. The app recently won one of the top prizes at the Swiss hackathon, LauzHack, and has captivated the international press’s attention. In November 2020, Coughvid gave precise prognostics at 80%, offering a great addition to the PCR test.

Finally, in early November, the center hosted an Open Campus Event in the presence of the Deans and CIS Collaboration grantees to present and discuss the early achievements and future ambitions of the center for 2021 and beyond.

Scroll
Research | 35 articles