Three PhD Positions on the Intersection of Formal Methods, Artificial Intelligence and Machine Learning

Three PhD Positions on the Intersection of Formal Methods, Artificial Intelligence and Machine Learning

Published Deadline Location
26 May 21 Jun Nijmegen

You cannot apply for this job anymore (deadline was 21 Jun 2020).

Browse the current job offers or choose an item in the top navigation above.

Job description

The Institute for Computing and Information Science at the Faculty of Science is looking for three excellent PhD candidates. Each position is dedicated to one of the following projects:

PrimaVera - Predictive maintenance for Very effective asset management
The overall challenge in the NWA-funded PrimaVera project is to fulfil the grand promises in predictive maintenance. Through an effective combination of sensor techniques, big data analysis, and maintenance engineering, we want to significantly improve failure predictions to render maintenance more effective. You will work on the intersection of formal methods (such as fault trees, stochastic model checking) and data analytics (decision trees, Bayesian Networks, neural networks, reinforcement learning, POMDPs). PrimaVera is a joint project with Eindhoven University of Technology, the University of Twente, Saxion, Hague University of Applied Sciences and the Dutch Aerospace Laboratory, as well as several industrial partners. You will be expected to participate in a fruitful collaboration with the industrial partners, for example, by carrying out an industrial case study. For more information, see https://primavera-project.com/ . The project will be supervised by Dr. Nils Jansen and Prof. Marielle Stoelinga.

Provably Correct Policies for Uncertain Partially Observable Markov Decision Processes
This NWO-funded project is dedicated to safety-critical artificial intelligence (AI) scenarios that may suffer from data uncertainty. In particular, we will bridge the gap between AI and formal methods through models that incorporate incomplete information and uncertain outcomes of decisions, namely partially observable Markov decision processes (POMDPs). The two central research goals are: (1) to develop scalable methods that guarantee decision making with hard guarantees on safety constraints under uncertainty, and (2) to render (deep) reinforcement learning to adhere to specifications during the exploration of uncertain and partially unknown POMDPs. The project is purely academic, but involves potential collaboration and research visits with well-known researchers from all over the world. The project will be supervised by Dr. Nils Jansen.

SAM-FMS - Scheduling Adaptive Modular Flexible Manufacturing Systems
SAM-FMS is an NWO-funded multi-partner project together with Eindhoven University of Technology, Delft University of Technology, ESI (TNO), and Canon Production Printing. The project will deliver new scheduling and co-design methods by pursuing model-driven synthesis approaches based on flow-shop models of manufacturing systems. We will employ and develop techniques from machine learning whose dependability is increased through formal methods and formal verification. You will work closely with the internal and external partners to help achieve the SAM-FMS project objectives. Specifically, close collaboration is needed with the industrial partners, the Electronic Systems group at Eindhoven University of Technology, and the Algorithmics group at Delft University of Technology. The project will be supervised by Dr. Nils Jansen and Prof. Frits Vaandrager.

Specifications

Radboud University

Requirements

  • You are an enthusiastic student with an MSc degree in Computer Science, as well as Engineering or Mathematics, with a demonstrable interest in computer science.
  • You should have a thorough theoretical background.
  • Experience with formal methods, probability theory, data analytics, and/or machine learning and artificial intelligence are helpful.

Conditions of employment

Fixed-term contract: you will be appointed for an initial period of 18 months, after which your performance will be evaluated. If the evaluation is positive, the contract will be extended by 2.5 years.

  • Employment: - 40 hours per week.
  • The gross starting salary amounts to €2,395 per month, and will increase to €3,061 in the fourth year (salary scale P)
  • In addition to the salary: an 8% holiday allowance and an 8.3% end-of-year bonus.
  • Duration of the contract: you will be appointed for an initial period of 18 months, after which your performance will be evaluated. If the evaluation is positive, the contract will be extended by 2.5 years.
  • The intended start date is 1 September 2020.
  • You will be able to make use of our Dual Career Service: our Dual Career Officer will assist with family-related support, such as child care, and help your partner prepare for the local labour market and with finding an occupation.
  • Are you interested in our excellent employment conditions?

Employer

Radboud University

We want to get the best out of science, others and ourselves. Why? Because this is what the world around us desperately needs. Leading research and education make an indispensable contribution to a healthy, free world with equal opportunities for all. This is what unites the more than 22,000 students and 5,000 employees at Radboud University. And this requires even more talent, collaboration and lifelong learning. You have a part to play!

Department

Faculteit der Natuurwetenschappen, Wiskunde & Informatica

The positions are available within the Institute for Computing and Information Sciences (iCIS) at the Faculty of Science. Research at iCIS focuses on software science, digital security and data science. During recent evaluations, iCIS has been consistently ranked as the No. 1 Computing Science department in the Netherlands. The Software Science group is well known for its contributions to the mathematical foundations of software, formal methods, AI, machine learning, and functional programming, with strong ties to international top researchers.

Specifications

  • PhD scholarship; PhD
  • Natural sciences
  • max. 40 hours per week
  • max. €3061 per month
  • University graduate
  • 1099526

Employer

Location

Houtlaan 4, 6525 XZ, Nijmegen

View on Google Maps

Interesting for you