PhD Scholarship in Next Generation AI Explainability

Updated: 2 months ago
Job Type: FullTime
Deadline: 01 Nov 2022

Can you help design more understandable AI algorithms?

DTU Compute 's Section for Cognitive Systems invites applications for a 3-year PhD position to investigate the properties of deep learning representations and improve their interactivity.

Make AI explanations more understandable

Machine learning algorithms often appear complex black boxes and much research has already gone into visualizing the hidden representations learned from data. The communication aspect of explainable AI has so far attracted less attention. Do you want to help us make learned representations more interactive?

The new Cognitive Spaces project aims at making AI explanations more understandable, robust and trustworthy. Your important part of the project will be to align representations better with cognitive processes and effectively let the algorithms speak the user’s language. Our primary application area is modeling and decision making based on electric brain waves (EEG).

Design and implement tools, apply your methods and present your research

During this PhD program your role will be to research latent representations, their structure, semantics and uncertainty. You will apply the methods to improve our understanding of EEG signals. You are expected to publish and present research results in AI conferences (e.g, NeurISP, ICML, ICASSP) and neuroimaging journals (Neural Computation, Neuroimage etc) as well as to contribute to open source tools. We also expect you to teach in relevant courses at DTU.

Master in Computer Science, Informatics, Computer Engineering, Applied Mathematics or equivalent

We are looking for candidates with:

  • A master’s degree (120 ECTS points) or a similar in Computer Science, Informatics, Computer Engineering, Applied Mathematics or equivalent
  • Proven experience in Python
  • Hands-on experience with deep learning frameworks
  • High level of motivation and innovation
  • Excellent written and communication skills in English

The research area is very active with many possibilities for collaboration and networking within academia, hospitals and there is a thriving start-up scene.

The scholarship is funded by a Novo Nordisk Foundation data science grant: Cognitive Spaces – next generation explainability.

Salary and appointment terms

The appointment will be based on the collective agreement with the Danish Confederation of Professional Associations. The allowance will be agreed upon with the relevant union. The position is a full-time position. The period of employment is 3 years, starting early 2023. 

You can read more about career paths at DTU here .   

Application procedure

To apply, please read the full job advertisement here: PhD scholarship in Next Generation AI Explainability

Application deadline: 1 November 2022

Technology for people

DTU develops technology for people. With our international elite research and study programmes, we are helping to create a better world and to solve the global challenges formulated in the UN’s 17 Sustainable Development Goals. Hans Christian Ørsted founded DTU in 1829 with a clear mission to develop and create value using science and engineering to benefit society. That mission lives on today. DTU has 13,400 students and 5,800 employees. We work in an international atmosphere and have an inclusive, evolving, and informal working environment. DTU has campuses in all parts of Denmark and in Greenland, and we collaborate with the best universities around the world.


View or Apply

Similar Positions