Action recognition and prediction in humans and AI
Project Description
This is a Cognitive Science project suitable for students who are interested in interdisciplinary research across CSE and SOSC.
We aim to examine how humans vs. AI recognise and predict/infer human actions and intentions. It will involve psychophysics, eye tracking, computational modelling, (optionally EEG), and comparisons between human and AI in terms of behaviour, performance, and underlying mechanisms.
We aim to examine how humans vs. AI recognise and predict/infer human actions and intentions. It will involve psychophysics, eye tracking, computational modelling, (optionally EEG), and comparisons between human and AI in terms of behaviour, performance, and underlying mechanisms.
Supervisor
HSIAO, Janet Hui-wen
Quota
2
Course type
UROP1100
Applicant's Roles
Experiment preparation, data collection, data analysis, result presentation and report preparation.
Applicant's Learning Objectives
- Have hands-on experience on interdisciplinary, cognitive science research.
- Understand the cognitive mechanisms underlying human action recognition and prediction, and how it can be implemented computationally.
- Understand the cognitive mechanisms underlying human action recognition and prediction, and how it can be implemented computationally.
Complexity of the project
Challenging