BEGIN:VCALENDAR
PRODID:-//eluceo/ical//2.0/EN
VERSION:2.0
CALSCALE:GREGORIAN
BEGIN:VEVENT
UID:www.tcs.tifr.res.in/event/1647
DTSTAMP:20251210T045840Z
SUMMARY:Learning to Model: Constraint Acquisition via Queries and Symbolic
 –Connectionist Hybridization
DESCRIPTION:Speaker: Nadjib Lazaar (University of Paris-Saclay)\n\nAbstract
 : \n\nConstraint Acquisition (CA) is a symbolic learning framework at the 
 intersection of concept learning (inductive reasoning) and constraint prog
 ramming (deductive reasoning). These two paradigms\, rooted in symbolic AI
 \, are combined in CA to automate and accelerate the modeling phase\, enab
 ling the automatic construction of constraint networks representing a targ
 et concept.\nIn Query-Based Constraint Acquisition (QBCA)\, the learner in
 teracts actively with an oracle by posing structured queries\, progressive
 ly refining the hypothesis space. This talk provides a structured overview
  of QBCA\, with a focus on the typology of queries (e.g.\, membership quer
 ies\, equivalence queries) and their role in the acquisition process. I wi
 ll also cover theoretical foundations\, recent algorithmic developments\, 
 and extensions to partial\, uncertain\, or qualitative contexts. QBCA open
 s promising avenues in applications such as program analysis\, autonomous 
 systems\, and interactive explainable modeling in XAI.\nFinally\, I will d
 iscuss emerging connections between QBCA and contemporary connectionist ap
 proaches\, notably language models (LLMs) and Transformers\, outlining dir
 ections for integrating explicit symbolic reasoning with statistical learn
 ing capabilities.\n \nShort Bio:Nadjib Lazaar is a Full Professor at Pari
 s-Saclay University and a member of the LaHDAK team at the LISN laboratory
 . He currently serves as director of the MIAGE program and co-director of 
 the Master's in Data Science at the Faculty of Sciences of Orsay. He is al
 so the International Relations Officer for the DATAIA Institute and the AI
  Cluster. Previously\, he was an Associate Professor (HDR) at the Universi
 ty of Montpellier from 2013 to 2024. His research sits at the intersection
  of Constraint Programming\, Data Mining\, Machine Learning\, and Software
  Engineering\, with a focus on constraint acquisition\, declarative data m
 ining\, AI-based software testing\, and trustworthy neuro-symbolic AI.\n
URL:https://www.tcs.tifr.res.in/web/events/1647
DTSTART;TZID=Asia/Kolkata:20251210T160000
DTEND;TZID=Asia/Kolkata:20251210T170000
LOCATION:HBA Foyer
END:VEVENT
END:VCALENDAR