Mark Hoogendoorn



I am a Full Professor of Artificial Intelligence at the Department of Computer Science of the Vrije Universiteit Amsterdam and chair of the Quantitative Data Analytics group.

My research focuses on machine learning and its applications, the latter primarily applied in the domain of health and wellbeing. The research ranges from more fundamental machine learning research (including efficiency, explainability, safety, incorporating domain knowledge, and hybrid intelligence) to application driven research focusing on for instance predictive modeling for diseases, personalized therapies and support systems, and eHealth and mHealth systems. For a list of my publications, click here. Together with my colleague Burkhardt Funk I have recently written a book on Machine Learning for the Quantified Self - On the Art of Learning from Sensory Data, published by Springer. You can find the website of the book here.

I am involved in a variety of research projects and teach several courses related to Artificial Intelligence and Machine Learning. In addition, I am the chair of the Examination Board (for the subcommittee for the Department of Computer Science) of the Faculty of Sciences. Below you can find more detail on all these aspects.

I also participate in a lot of research centers and organizations. I am currently a member of the Board of Directors of ISRII and chair the Special Interest Group on Data Standards and Sharing in the same organization. I am also a member of the Management Team of Amsterdam Medical Data Science and part of the Management Team of the VU Campus Center for AI & Health. In addition, I am a member of Amsterdam Data Science, the Network Institute, and the Amsterdam Center for Business Analytics.

Before starting in the Quantitative Data Analytics group, I have been an Associate Professor in the Computational Intelligence group. I have also been a Visiting Scientist within the Clinical Decision Making Group headed by Peter Szolovits at MIT (CSAIL) during the Summer of 2015 and a PostDoc at the Department of Computer Science and Engineering at the University of Minnesota in the group of Maria Gini (Fall 2007). Before 2012 I was part of the Agent Systems Group at the VU. I obtained my PhD degree in 2007 from the Vrije Universiteit Amsterdam as well.

Next to my academic work, I have also founded the company PersonalAIze together with three colleagues to bring academic insights in the area of Machine Learning into practice.

Team

  • Frank Bennis (PostDoc)
  • Tariq Dam (PhD student)
  • Lucas Fleuren (PhD student)
  • Anne Fischer (PhD student)
  • Vincent Francois Lavet (Assistant Professor)
  • Eoin Grua (PhD student)
  • Ali el Hassouni (PhD student)
  • Floris den Hengst (PhD student)
  • Jan Klein (PhD student)
  • Olivier Moulin (PhD student)
  • Luca Roggeveen (PhD student)
  • David Wilson Romero Guzman (PhD student)
  • Luis Silvestrin (PhD student)

Research Projects

I am currently involved in various research projects:

  • Personalized smart health apps. Development of techniques to learn to provide feedback and support to users in an effective way by means of health apps on their smart phone. This project is funded by Mobiquity Inc.

  • Constrained personalization of smart health apps. In this project, we aim to develop machine learning techniques to personalize applications within certain boundaries. This project is a collaboration with the Software and Services Group of the VU (Patricia Lago and Ivano Malavolta).

  • Machine Learning for Intensive Care. This project aims to develop predictive models based on Electronic Medical Records for the Intensive Care department at the VU University Medical Center using machine learning techniques to improve medical decision making. The project is a collaboration with Paul Elbers and Armand Girbes.

  • Predictive modeling and outlier detection for large datasets. A joint project with the Ministry of the Interior, the Department of Mathematics of the VU (Sandjai Bhulai), and the Center for Mathematics and Computer Science (Rob van der Mei).

  • Constrained reinforcement learning for personalization in highly regulated domains. In the project, the aim is to develop constrained personalization approaches using machine learning. This project is funded by ING and is a collaboration with the Knowledge Representation and Reasoning group at the VU (Frank van Harmelen).

  • RESCUED. The identification of risk factors and creation of predictive models for cardiac arrest among diabetes patients using machine learning is the main goal of this project. This project is a collaboration with the VUmc, AMC, and LUMC and is funded by CVON (a funding scheme by NWO, the Hartstichting and the joint university medical centers).

  • PIPPI. This project concerns the identification of risk models for mental health problems among children and adolescents using data from general practitioners and the municipality health services. This project is a collaboration with the LUMC and is funded by NWO (ZonMW).

  • Efficient Deep Learning. In this project, funded by NWO (TTW), the goal is to improve the efficiency of deep learning algorithms. The project is a collaboration with various research institutes (UvA, CWI, TUE) as well as companies.

  • EFRO Smart Maintenance. In this project, funded by the EU (EFRO), the goal is to use and improve machine learning techniques for predictive maintenance and optimization of maintenance. The project is a collaboration with the Department of Mathematics of the VU (Ger Koole)
  • COCOON. This project, which is funded by HealthHolland, concerns the prediction of pre-term birth using a variety of data sources (including Electrohysterography) using machine learning. The project is a collaboration with the Amsterdam UMC (Anna Rietveld, Petra Bakker), Bloomlife Inc., and the Maastricht UMC+ (Pim Teunissen).
  • IMPALA. A project funded by the European & Developing Countries Clinical Trials Partnership (EDCTP), focuses on development of innovative sensors with machine learning algorithms timely detect and predict critical illness in low resource settings. The project is a collaboration with a variety of partners across Europe and coordinated by Amsterdam Institute for Global Health and Development (AIGHD).
  • ICARE4OLD. The overall objective of the I-CARE4OLD project (H2020 EU project) is to develop high quality decision support for better prognostication of health trajectories, including treatment impact, in older care recipients with complex chronic conditions using linked real world data. Our focus in the project is on the development of novel machine learning algorithms (both supervised learning and reinforcement learning) to create accurate predictions on the impact of treatments.

Teaching

I teach several courses. Information regarding the courses I teach can be found on Canvas. I'm currently involved in teaching/coordinating the following courses:
  • Data Mining Techniques
  • Machine Learning for the Quantified Self
  • Bedrijfscase
  • Mini Master Project (coordinator)

Contact Details

email: m.hoogendoorn@vu.nl

phone: +31 20 598 7772

office: 10A-87 of the NU.VU building (map)

postal address:
Prof. dr. Mark Hoogendoorn
Vrije Universiteit Amsterdam
Faculty of Science
Department of Computer Science
De Boelelaan 1111
1081 HV Amsterdam
The Netherlands