BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20260730T095918Z
UID:85237836-5257-40be-81ed-07fa71d56daf
DTSTART:20261105T130000Z
DTEND:20261105T140000Z
DESCRIPTION:Speakers: Saso Dzeroski (Jozef Stefan Institute)\n\nArtificial 
 intelligence is already transforming science\, with its future impact expe
 cted to be even greater. Realizing this potential requires addressing key 
 scientific challenges\, such as ensuring explainability (of models and the
 ir predictions)\, learning effectively from limited data\, and integrating
  data with prior domain knowledge. It also requires the provision of suppo
 rt for open and reproducible science through formalizing and sharing scien
 tific knowledge.\nI will present an overview of my research on the develop
 ment of AI methods suitable for use in science. These include methods for 
 explainable machine learning — including multi-target prediction and rel
 ational learning — that deliver accurate yet interpretable models suitab
 le for complex scientific domains. These methods have been applied in envi
 ronmental science\, life science and materials science.\nLearning from lim
 ited data is critical in science. I will discuss two complementary approac
 hes: semi-supervised learning\, which leverages unlabeled data directly\, 
 together with labeled data\, and foundation models\, which use representat
 ions learned from vast unlabeled data to support downstream tasks with min
 imal supervision\, i.e.\, limited amounts of labeled data. Both paradigms 
 expand AI’s reach into data-scarce scientific problems.\nI will then pre
 sent our work on automated scientific modeling\, where we learn interpreta
 ble models of dynamical systems — such as process-based models and diffe
 rential equations — from time series data and domain knowledge. Finally\
 , I will highlight the role of ontologies and semantic technologies in exp
 erimental computer science\, including machine learning and optimization. 
 In these areas\, we have developed ontologies for the representation and a
 nnotation of both data and other artefacts produced by science\, such as a
 lgorithms\, models\, and results of experiments.\nSašo Džeroski is Head 
 of the Department of knowledge technologies at the Jozef Stefan Institute 
 and full professor at the Jozef Stefan International Postgraduate School\,
  both in Ljubljana\, Slovenia. He is a fellow of EurAI\, the European Asso
 ciation of AI\, in recognition of his "Pioneering Work in the field of AI
 ”. He is a member of the Macedonian Academy of Sciences and Arts and a m
 ember of Academia Europea. He is past president and current vice-president
  of SLAIS\, the Slovenian Artificial Intelligence Society.\nHis research i
 nterests focus on explainable machine learning\, computational scientific 
 discovery\, and semantic technologies\, all in the context of artificial i
 ntelligence for science. His group has developed machine learning methods 
 that learn explainable models from complex data in the presence of domain 
 knowledge: These include methods for multi-target prediction\, semi-superv
 ised and relational learning\, and learning from data streams\, as well as
  automated modelling of dynamical systems.\nProfessor Džeroski has lead (
 as coordinator) many national and international (EU-funded ) projects and 
 has participated in many more. He is also the technical coordinator of the
  Slovenian Artificial Intelligence Factory. The work of professor Džerosk
 i has been extensively published and is highly cited: With more than 27000
  citations and an h-index of 75 (in the GoogleScholar database)\, prof. D
 žeroski is the most frequently cited computer scientist in Slovenia (acco
 rding to the 2025 ranking by Research.com). \n\nhttps://indico.cern.ch/ev
 ent/1601617/\n\nZoom: https://cern.zoom.us/j/98545267593?pwd=akZWdmlyK01zb
 jFQa0x2c2ZXWW9ydz09
LOCATION:CERN
SUMMARY:Artificial Intelligence for Science
URL;VALUE=URI:https://indico.cern.ch/event/1601617/
END:VEVENT
END:VCALENDAR