The research group: Distributed Machine Learning, part of imec-IDLAB-UGent
IDLab is a research group of Ghent University, as well as a core research group of imec. IDLab performs fundamental and applied research on data science and internet technology, and counts over 300 researchers. IDLab is also part of imec, the world-leading research and innovation hub in nanoelectronics and digital technologies. The combination of our widely acclaimed leadership in microchip technology and profound software and ICT expertise is what makes us unique.
This position is within the research group Distributed Machine Learning. This group focuses on innovative machine learning techniques in situations where intelligence is divided between multiple entities, be it multiple robots, edge device and cloud-backend, or human-AI interaction. This position is situated in the latter domain, and will be carried out within the context of a prestigious FET project.
We are heading towards a hybrid society, where AI-enabled agents cooperate with humans in a variety of tasks. Human decision making is however notably prone to cognitive biases. In applications supporting the human, the integrated AI should account for these biases when making suggestions or taking actions. Within the context of a prestigious European FET-OPEN collaborative project (ChronoPilot), the Phd study recruited for this position will design a computational model that generates multi-modal (audio, video, haptic) stimuli via XR technology to resolve the differences in individual time perception during group tasks.
The perception of time is a critical component of a large range of human activities. In particular, when individuals have to make decisions and consider the outcomes associated with their choices. Nevertheless, humans perceive durations mostly subjectively. Sometimes time flies, whereas at other moments, time feels expanded, depending on the individual’s environment, the task at hand, the allocation of the individual’s attention, etc. This subjective judgment of durations influences the optimality of human decisions, well-being, performance, etc. While the focus of this position is on the computational modelling using AI techniques, the researcher will closely collaborate with researchers from other disciplines.
Psychological experiments have shown that humans estimate time duration differently when they are presented with particular stimuli, like flickering dots or beeps. It is thus possible to modulate the duration of a perceived interval by presenting well-chosen stimuli. However, these experiments were conducted in well-controlled laboratory environments with very elementary stimuli. In this project, we aim to develop a set of computation models that can predict and modulate human time perception in a large set of experiments and in more realistic—thus less-controlled— environments. Among many other techniques, we will explore techniques such as Bayesian models and predictive coding to design our adaptive computational models.
The goal of the current PhD position is to model, build and test the AI component that extracts features from the scene observed by the human as well as physiological signals (e.g. to derive stress), and that outputs an estimation of the subjective time as well as possible stimuli to modulate the subjective time experience in the desired direction. The computational model will be designed and tested in tight collaboration with another PhD researcher in our group.
The hired candidate will work on this topic in the context of the FET ChronoPilot project; in collaboration with project partners from Greece, Luxemburg, Germany and Belgium. The hired candidate is responsible for the design of the computational models, and for the integration in a working prototype. The candidate will collaborate with students with a background in psychology to evaluate the models in experiments with volunteers, and with students with a background in VR/AR to design the environments.
- Design, development, and implementation of a computational model of subjective time experience. These models take as input environmental stimuli, task-related stimuli as well as the affective state, and output a subjective time estimation.
- Validation of these models through user experiments, and interpretation of the results in tight collaboration with psychologists.
- Integration of these models into a working prototype, in cooperation with other technical partners.
- Close international and interdisciplinary collaboration (especially psychology) with project partners from Germany, Greece, and Luxembourg
- Independent work on a diverse set of tools and methods (e.g., machine learning, multi-robot simulations and experiments with hardware, VR/AR)
- Collaboration on publications and presentations at international conferences
- Supervision of master theses related to the subject of this PhD
- You have a degree in Master of Science/Engineering, preferably in computer science, computational neuroscience or cognitive science. To be admissible to the PhD-program, your degree must be equivalent to 5 years of engineering studies (bachelor + master) in the European Union.
You have a solid academic track record (graduation cum laude or grades in the top 10%). Please do not hesitate to contact us regarding these administrative matters.
- You have proven knowledge of machine learning.
- You have a strong interest in one or more of the following domains: cognitive modelling, computational neuroscience, Bayesian machine learning. Proven experience in one of these domains, e.g. via your master thesis topic or projects, is a plus (but not a necessity).
- Besides computational modelling, you are willing to engage in hands-on implementation and prototyping to develop proof-of-concepts.
- You are interested in working with other researchers in a multidisciplinary setting, in particular with psychologists to set-up user experiments.
- You speak and write English fluently (C1 CEFR level).
- You have good communication skills.
- You are eligible for a Flemish PhD scholarship (i.e., you have not enjoyed such a scholarship before).
We offer a fully funded PhD scholarship for a maximal period of 4 years (upon positive progress evaluation after the first year). The PhD research is fundamental and innovative, but with clear practical applications. You will join a young and enthusiastic team of researchers, post-docs and professors. The PhD position is immediately available.
How to apply
Apply with CV, motivation letter, abstract of your master thesis, diplomas and detailed academic results (courses and grades). This information, as well as possible questions, must be sent to Prof. Pieter Simoens at firstname.lastname@example.org
After the first screening, suitable candidates will be invited for an interview (also possible via teleconference). This interview is the first stage of a multi-stage application procedure. Applications will be screened as soon as they are received. The position is open until the vacancy is filled.
Tentative starting data: Fall 2022