PhD position in Machine Learning in the Space of Dynamical models


Faculty of Science and Engineering


University of Groningen

Since its foundation in 1614, the University of Groningen has enjoyed an international reputation as a dynamic and innovative centre of higher education offering high-quality teaching and research. Balanced study and career paths in a wide variety of disciplines encourage currently more than 35,000 students and researchers to develop their own individual talents. Belonging to the best research universities in Europe and the top 100 universities in the world (see our ranking:, the University of Groningen is truly an international place of knowledge.

Within the Faculty of Science and Engineering (FSE), the Bernoulli Institute conducts research combining theoretical as well as practical aspects of three disciplines, namely Mathematics, Computer Science and Artificial Intelligence. The environment fosters truly interdisciplinary research with a great track record of national and international collaboration transferring knowledge across domains. The research unit Intelligent Systems (IS) in Computer Science is focused on the development of Data Science, Pattern Recognition and Machine Learning algorithms for interdisciplinary data analysis with applications in Robotics, Astronomy, Smart Industry and Medicine. The Machine Learning thrust within IS in particular focuses on subjects related to (1) Explainable Artificial Intelligence or interpretable Machine Learning, (2) Manifold Learning, (3) the theory of learning and (4) interdisciplinary data analysis. For more information about the Intelligent Systems group please use the following link:

Job description

PhD advertisement of project on “machine learning in the space of dynamic models” within the NWO Vidi project on "Mechanistic machine learning: combining the explanatory power of dynamic models with the predictive power of machine learning."

Project description
Nowadays, most successful machine learning (ML) techniques for the analysis of complex systems require significant amounts of data. The domain expert knowledge is often only used in data preprocessing or to provide label information. The subsequently trained technique appears as a “black box”, which is difficult to interpret and rarely allows insight into the underlying natural process. Especially in critical domains such as medicine and engineering, the analysis of dynamic data in the form of sequences and time series is often difficult. Due to natural or cost limitations and ethical considerations data is often irregularly and sparsely sampled and the underlying dynamic system is complex. Therefore, domain experts currently enter a time-consuming and laborious cycle of mechanistic model construction and simulation, often without direct use of the experimental data or the task at hand.

Recently, the team published a hybrid approach combining the predictive power of ML and the explanatory power of pharmacokinetic models for model-based clustering, automatically determining groups of responses to medication in a clinical data set. In this Vidi-project, we aim to formulate a generalised framework for learning in the space of dynamic models that represent the complex underlying natural processes, with potentially very few measurements. This will be achieved by incorporating expert knowledge in the form of mechanistic models (such as Ordinary, Stochastic or Partial Differential Equations) and their structural properties.

This project has the potential to foster the acceptance of ML in critical domains, such as medicine and engineering. This will be demonstrated with application in the area of healthy ageing, for personalised medicine and treatment monitoring based on pathway and pharmacokinetic models, as well as engineering, for fault detection based on models of the production process.

Position description
In this advert, we will hire a PhD student who will focus on the development of machine learning algorithms that incorporate expert knowledge in form of mechanistic models of dynamic systems. It is expected that the PhD student will collaborate with other PhD students within the Vidi project and our close collaborators at the University of Birmingham in the UK.


We welcome applications if you have a:

• MSc degree in Computer Science, Engineering, Mathematics, Theoretical Physics or other degree programmes from top universities involving at least one of the following topics: Machine Learning, Dynamic Systems (ODE, SDE or PDE), Monte Carlo methods, Differential Geometry and/or Information Theory
• strong academic credentials, written and spoken English proficiency
• strong knowledge and interest in Mathematics
• a dynamic, creative and pioneering professional attitude with a willingness to work in a strongly interdisciplinary team and learn the cross-disciplinary foundations
• problem solving ability
• strong communication skills.

Conditions of employment

Contract length: 48 months.

The University of Groningen offers, in accordance with the Collective Labour Agreement for Dutch Universities:

• a salary of € 2,395 gross per month in the first year, up to a maximum of € 3,061 gross per month in the fourth and final year for a full-time working week
• a full-time position (1.0 FTE)
• a holiday allowance of 8% gross annual income
• 8.3% year-end bonus
• the position requires residence in Groningen and must result in a PhD thesis within the 4-year contract period (the candidate is required to move to Groningen in case of successful application. We do not accept long commute times or remote work for a substantial part of the contract)
• the successful candidate will first be offered a temporary position of one year with the option of renewal for another three years; prolongation of the contract is contingent on sufficient progress in the first year to indicate that a successful completion of the PhD thesis within the next three years is to be expected
• a PhD training programme is part of the agreement and the successful candidate will be enrolled in the Graduate School of Science and Engineering.

The preferred starting date is before summer 2021

Job Application

Application should include:

• letter of motivation
• CV (including contact information for at least two academic references)
• a list of publications (if any)
• transcripts from your bachelor’s and master’s degree.

The applications can be submitted until 28 February 2021 23:59h / before 1 March 2021 Dutch local time by means of the application form (click on "Apply" below on the advertisement on the university website).

Applications received before 1 March 2021 will be given full consideration.

We are an equal opportunity employer and value diversity at our University. We are committed to building a diverse faculty so you are encouraged to apply. Our selection procedure follows the guidelines of the Recruitment code (NVP), and European Commission's European Code of Conduct for recruitment of researchers,

Unsolicited marketing is not appreciated.

Additional information

For additional information, please contact:

Dr K. Bunte

In your application, please always include the job opening ID 221007

Digital application form