explainable machine learning (rule learning)
psychology in machine learning (cognitive biases)
natural language processing (entity recognition, knowledge graphs)
preference learning, utility theory
2019: docent (Associate professor) - Applied Informatics. VSE Praha.
2017: PhD. Research in Electronic Engineering. School of Computer Science and Electronic Engineering, Queen Mary University London. Degree recognized in the Czech Republic as Ph.D. in Artificial Intelligence and Biocybernetics.
Thesis: "EFFECT OF COGNITIVE BIASES ON HUMAN UNDERSTANDING OF RULE-BASED MACHINE LEARNING MODELS". Results partly published in:
Tomáš Kliegr, Štěpán Bahník, Johannes Fürnkranz. "A review of possible effects of cognitive biases on the interpretation of rule-based machine learning models". Artificial Intelligence. In print.
Fürnkranz, Johannes, Tomáš Kliegr, and Heiko Paulheim. "On cognitive preferences and the plausibility of rule-based models." Machine Learning 109.4 (2020): 853-898.
Kliegr, Tomáš, Ebroul Izquierdo. "QCBA: improving rule classifiers learned from quantitative data by recovering information lost by discretisation" Applied Intelligence. Springer. 2023. Alsoin CRAN package qCBA.
2012: PhD. in Applied Informatics. Faculty of Informatics and Statistics, VSE Praha
Thesis: "UNSUPERVISED ENTITY CLASSIFICATION WITH WIKIPEDIA AND WORDNET". Results partly published in two articles in the Journal of Web Semantics:
Kliegr, Tomáš. "Linked hypernyms: Enriching DBpedia with targeted hypernym discovery." Journal of Web Semantics 31 (2015): 59-69.
Kliegr, Tomáš, and Ondřej Zamazal. "LHD 2.0: A text mining approach to typing entities in knowledge graphs." Journal of Web Semantics 39 (2016): 47-61.
Fellow of AI Czechia, Czech Society for Cybernetics and Informatics (Artificial Intelligence working group), Gesellschaft für Klassifikation (Data Science Society), DBpedia association