Job description
***PhD position on Artificial Intelligence for modulating human time perception***
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.
Job profile
This PhD position is fully funded for 4 years.
Main tasks:
- Design, development, and implementation of AI techniques for modelling subjective time experience in multi-person settings. These models take as input environmental stimuli, task-related stimuli as well as physiological state measured via sensors, and output a subjective time.
- 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 using VR/AR glasses and robots, in cooperation with other technical partners. You also assist in the evaluation of the prototype, in cooperation with partners who have expertise in psychology.
- Independent work on a diverse set of tools and methods (mainly machine learning, VR/AR and real-life demonstrators)
- Collaboration on publications and presentations at international conferences
- Supervision of master theses related to the subject of this PhD
Requirements
- You have a master degree in Computer Science, Artificial Intelligence or equivalent. To be admissible to the PhD-program, your degree must be equivalent to 5 years of studies (bachelor + master) in the European Union. Last year students are also welcome to apply.
- You have a solid academic track record (graduation cum laude or grades in the top 10%).
- You have a strong interest in one or more of the following domains: cognitive modelling, computational neuroscience or (advanced) machine learning (e.g. deep learning, Bayesian, probabilistic graphical models, etc.).
- Besides computational modeling, you are willing to engage in hands-on implementation and prototyping. Proven hands-on experience in one of the domains, e.g. via your master thesis topic or projects, is a necessity.
- You are interested in working with other researchers in a multidisciplinary and European setting, in particular with psychologists to set-up user experiments. When needed, you should be willing to spend short research stays in other European countries.
- You speak and write English fluently (C1 CEFR level).
- You have good communication skills.
The recruited candidate can start immediately.
How to apply
Please send your CV, an overview of your grades and a motivation letter to pieter.simoens@ugent.be. There is no deadline: applications will be reviewed immediately.