Séminaire Donnees et APprentissage Artificiel
Transparent modelling of uncertainty - a role for fuzzy sets and systems in XAI?
Speaker(s) : Christian Wagner (Univ. of Nottingham)
While fuzzy sets and systems are often credited with being useful for modelling uncertainty and for being interpretable, it is straightforward to argue that they are neither. With both uncertainty handling and interpretability being 'hot topics' in AI, in this talk I reflect on the capacity of fuzzy sets and systems to transparently model and handle uncertainty, focussing in particular on data-driven fuzzy set design and novel approaches to non-singleton fuzzy logic systems.
In respect to the latter, I will discuss their utility in respect to 'performance' but also more generally in respect to the important reason they play in the systematic and transparent modelling of uncertainty affecting system inputs. Finally, time permitting, I will focus on how to capture uncertainty in the real world, presenting recent interdisciplinary work at the interface of computer and the social sciences.
Christian Wagner is an Associate Professor in Computer Science at the University of Nottingham, and founding director of the Lab for Uncertainty in Data and Decision Making (LUCID). He has published over 100 peer-reviewed articles, focussing on modelling & handling of uncertain data arising from heterogeneous data sources (e.g. stakeholders), with a particular emphasis on designing interpretable AI based decision support systems. In 2017, he was recognised as a RISE (Recognising Inspirational Scientists and Engineers) Connector by EPSRC. His work ranges from decision support in cyber security and environmental management to personalisation and control in manufacturing. He has led ten and co-led three research projects with partners from industry and government with an overall value of over £9.3m and co/developed multiple open source software frameworks, making cutting edge research accessible to research communities beyond computer science.
Dr Wagner is an Associate Editor of the IEEE Transactions on Fuzzy Systems journal, Chair of the IEEE CIS Technical Committee on Fuzzy Systems and Task Force on Cyber Security; elected member-at-large of the IEEE Computational Intelligence Society (CIS) Administrative Committee for 2018-2020. He is a General Chair of Fuzz-IEEE 2021 in Luxembourg and Special Sessions Chair at Fuzz-IEEE 2019 in New Orleans.
_Plus d'information sur Christian Wagner :_
More details here
benjamin.piwowarski (at) nulllip6.fr