Welcome...

dr.ir. M. van Keulen (Maurice)

Associate Professor

About Me

He received his masters’ degree in computer science at the University of Twente in 1992 and completed his PhD on Formal operation definition in object-oriented databases in 1997. His research targets robustness in data science focusing on two main threats to data science reliability: data quality and undesirable machine learning behaviour. The former is focused on data integration, semi-structured data, natural language processing, and data quality issues involved in these. He co-developed one of the most scalable XML database systems of its time: MonetDB/XQuery. Furthermore, he proposed a data integration approach, called Probabilistic Data Integration, which fundamentally incorporates handling of uncertain and of lesser quality data. He developed a probabilistic database system, called DuBio, which allows the scalable storage, manipulation and management of such uncertain data. On the threat of undesirable machine learning behaviour, he focuses on Explainable AI with the intrinsically explainable deep learning approach ProtoTree as one of the notable results of this. He is secretary of the executive board of the EDBT Association (Extending Database Technology). He is the (co-) author of about 200 publications that accumulated about 2000 citations.

Expertise

Engineering & Materials Science
Big Data
Data Integration
Machine Learning
Metadata
Ontology
Radiology
Semantics
Uncertainty

Publications

Recent
Nauta, M., Hegeman, J. H., Geerdink, J., Schlötterer, J. , Keulen, M. V. , & Seifert, C. (2024). Interpreting and Correcting Medical Image Classification with PIP-Net. In S. Nowaczyk, P. Biecek, N. C. Chung, M. Vallati, P. Skruch, J. Jaworek-Korjakowska, S. Parkinson, A. Nikitas, M. Atzmüller, T. Kliegr, U. Schmid, S. Bobek, N. Lavrac, M. Peeters, R. van Dierendonck, S. Robben, E. Mercier-Laurent, G. Kayakutlu, M. L. Owoc, K. Mason, A. Wahid, P. Bruno, F. Calimeri, F. Cauteruccio, G. Terracina, D. Wolter, J. L. Leidner, M. Kohlhase, ... V. Dimitrova (Eds.), Artificial Intelligence. ECAI 2023 International Workshops - XAI^3, TACTIFUL, XI-ML, SEDAMI, RAAIT, AI4S, HYDRA, AI4AI, 2023, Proceedings (pp. 198-215). (Communications in Computer and Information Science; Vol. 1947). Springer. https://doi.org/10.1007/978-3-031-50396-2_11
Maas, J., Römer, J. G. W. T. , Baysal Erez, I. , & van Keulen, M. (2023). Investigating Imputation Methods for Handling Missing Data. Poster session presented at Joint International Scientific Conferences on AI and Machine Learning, BNAIC/BeNeLearn 2023, Delft, Netherlands.
Maas, J., Römer, J. G. W. T. , Baysal Erez, I. , & van Keulen, M. (2023). Investigating Imputation Methods for Handling Missing Data. Paper presented at Joint International Scientific Conferences on AI and Machine Learning, BNAIC/BeNeLearn 2023, Delft, Netherlands.
Xiao, Q. , Wu, B., Yin, L. , van Keulen, M., & Pechenizkiy, M. (2023). Can Less Yield More? Insights into Truly Sparse Training. Poster session presented at ICLR 2023 Workshop on Sparsity in Neural Networks, Kigali, Rwanda. https://drive.google.com/file/d/1kbWZ9ejU9XvtOMRtAcVYmcoRCDIWj3zy/view
Nauta, M., Schlötterer, J. , van Keulen, M. , & Seifert, C. (2023). PIP-Net: Patch-Based Intuitive Prototypes for Interpretable Image Classification. Abstract from 2nd Explainable AI for Computer Vision Workshop, XAI4CV 2023, Vancouver, British Columbia, Canada.
Nauta, M. (2023). Explainable AI and Interpretable Computer Vision: From Oversight to Insight. [PhD Thesis - Research UT, graduation UT, University of Twente]. University of Twente. https://doi.org/10.3990/1.9789036555753
Tran, T. H. A., Wiesner, M. L. , & van Keulen, M. (2022). Influence of discretization granularity on learning classification models. Paper presented at BNAIC/BeNeLearn 2022 Joint International Scientific Conferences on AI and Machine Learning, Mechelen, Belgium. https://bnaic2022.uantwerpen.be/BNAICBeNeLearn_2022_submission_8652

UT Research Information System

Google Scholar Link

Affiliated Study Programmes

Bachelor

Master

Courses Academic Year  2023/2024

Courses in the current academic year are added at the moment they are finalised in the Osiris system. Therefore it is possible that the list is not yet complete for the whole academic year.
 

Courses Academic Year  2022/2023

Contact Details

Visiting Address

University of Twente
Faculty of Electrical Engineering, Mathematics and Computer Science
Zilverling (building no. 11), room 4061
Hallenweg 19
7522NH  Enschede
The Netherlands

Navigate to location

Mailing Address

University of Twente
Faculty of Electrical Engineering, Mathematics and Computer Science
Zilverling  4061
P.O. Box 217
7500 AE Enschede
The Netherlands

Social Media