AI-Fun with ELLIS Seminar | Fabio Cuzzolin
| Dates: | 27 November 2024 |
|---|
| Times: | 11:00 - 12:00 |
|---|
| What is it: | Seminar |
|---|
| Organiser: | Faculty of Science and Engineering |
|---|
| Who is it for: | University staff, External researchers, Alumni, Current University students |
|---|
| Speaker: | Fabio Cuzzolin |
|---|
|
The Manchester Centre for AI Fundamentals and Manchester's ELLIS Unit are co-hosting a series of seminars featuring expert researchers working in the fundamentals of AI.
Fabio Cuzzolin short bio:
I am a Professor of Artificial Intelligence and the Director of the Visual Artificial Intelligence Laboratory, a thriving research unit comprising around 35-40 people, including permanent staff, paid researcher and members at large. I am also in the Board of Oxford Brookes' Institute of Ethical AI and of the Healthy Ageing and Care (HAC) network.
I am a recognised leader in the field of uncertainty theory and belief functions, as conference chair, four-term member of the Board of Directors of the Belief Functions and Applications Society (BFAS), former Executive Editor of SIPTA (the Society for Imprecise Probabilities) and editor of journals such as IJAR and IEEE TFS. My reputation there comes from the formulation of a geometric approach to uncertainty in which various measures are analysed by geometric means. This work has led to two monographs, two edited volumes and various tutorials and invited talks at top universities and venues. More in general, I am widely contributing to the mathematical foundations theory of random sets (generalised laws of probability, generalised statistical inference and random variables), with the aim to make it a viable alternative to probabilistic reasoning.
Within artificial intelligence at large my work is directed at providing new robust foundations for statistical learning theory via uncertainty theory, and developing novel tools based on the theory of random sets, e.g. the generalisation of the logistic regression and max-entropy classification frameworks. In the past I also worked on manifold learning for dynamical models and the generalisation of bilinear classifiers to the tensorial case (EPSRC First Grant). Since 2016 my interests and the activities in my group have been expanding towards surgical robotics (via the H2020 SARAS project of which I am Scientific Officer, and the recent EPSRC MAESTRO Jr project with Imperial College), AI for healthcare (via joint papers and bids with Prof Helen Dawes and Prof Derick Wade), cognitive artificial intelligence (see my Leverhulme machine theory of mind grant with Cambridge Neuroscience) and autonomous driving (via a collaboration with Federico II University, Naples and OBR - Autonomous). Very recently I have been strongly promoting the injection of second-order uncertainty into the very foundations of artificial intelligence, in particular through my recent H2020 FET ‘Epistemic AI’, neurosymbolic learning (in collaboration with Oxford University and Samsung AI) and continual learning, in particular in the semi-supervised setting, in collaboration with ContinualAI.
Title and location to follow.
Travel and Contact Information
Find event
Lecture Theatre 1.4
Kilburn Building
Manchester
