Markov Logic Networks: A step towards interpretable AI

Speaker: Vladimir Despotovic (Faculty of Science, Technology and Medicine; University of Luxembourg)
Title: Markov Logic Networks: A step towards interpretable AI
Time: Wednesday, 2021.10.27, 10:00 a.m. (CET)
Place: fully virtual (contact Jakub Lengiewicz to register)
Format: 30 min. presentation + 30 min. discussion

Abstract: Markov Logic Networks are highly expressive statistical relational models that combine complex relational information expressed by the first-order logic formulas with the uncertainty represented by the use of the undirected probabilistic graphical models (Markov networks). They allow for representation of a relational structure and uncertainty in a very compact manner, leading to human-interpretable models. In this talk we will discuss the theoretical background of the Markov logic networks and showcase the application in the spoken language understanding domain.