In the era of the Internet of Things and Big Data, data scientists are aimed for finding out valuable
knowledge from data. They first analyze, cure and pre-process data. Then, they apply Artificial
Intelligence techniques to automatically extract knowledge from data and afterwards translating
knowledge into products and services for economic growth and social benefit. Trustworthy AI is an
endeavor to evolve AI methodologies and technology by focusing on generating a new generation of
intelligent devices which respect non-discrimination and fairness with the ability to explain their
decisions to humans. Furthermore, when it comes to consider the impact of AI systems on human
behavior, several dimensions have to be addressed, being the most well-known among them the ethical,
legal, social, economic, and cultural issues.
Explainable Fuzzy Systems born with the aim of paving the way from interpretable machine learning to
Explainable AI. Such systems deal naturally with uncertainty and approximate reasoning (as humans do)
through computing with words and perceptions. This way, they facilitate humans to scrutinize the
underlying intelligent models and verify if automated decisions are made based on accepted rules and
principles, so that decisions can be trusted and their impact justified. Notice that, EXFS automatically
generate factual and counterfactual verbal and non-verbal explanations. Such explanations include
linguistic pieces of information which embrace vague concepts representing naturally the uncertainty
inherent to most activities in the everyday life.
In this colloquium, we will begin with a non-technical introduction to the field of TAI (i.e., revisiting
definitions and fundamentals, reviewing the state of the art and enumerating open challenges). Then, we
will briefly review the history of fuzzy systems from the pioneer works of L.A. Zadeh to the most recent
developments on EXFS, with special emphasis on fuzzy-grounded knowledge representation and
reasoning, as well as how to use EXFS to deal with imprecision and uncertainty in the contexts of XAI
and TAI. Finally, we will see some practical software tools as well as critical issues related to
psycholinguistic human evaluation.
Jose M. Alonso-Moral received his degrees in Telecommunication Engineering, from the Technical
University of Madrid, Spain. He is currently “Ramón y Cajal” researcher funded by the Spanish
Government, affiliated to CiTIUS-USC, President of the Executive Board and Deputy Coordinator of the
project “Interactive Natural Language Technology for Explainable Artificial Intelligence”, Chair of the
IEEE-CIS TF on Explainable Fuzzy Systems, member of the IEEE-CIS TF on Explainable Machine
Learning, member of the IEEE-CIS WG on eXplainable AI, member of the IEEE-CIS TF on Fuzzy
Systems Software, board member of the ACL SIG on Natural Language Generation. He has published
more than 160 papers in international journals, book chapters and conferences and is co-author of the
book "Explainable Fuzzy Systems”
When and Where?
Date and time: Thursday, October 27nd, 2022, 11.00 pm
Location: Pérolles 21, room E230, Bd de Pérolles 90, Fribourg
The colloquium is free and open to the public
Here the zoom link: https://us02web.zoom.us/j/83658692810?pwd=WWRLZ2VkS0NHaUFJOVQzQkxJc3V4Zz09?