PhD Project: Computational models of mental workload with deep learning and symbolic reasoning

The project will focus on multi-disciplinary research in the area of Mental Workload (MWL) modelling. It will lead to a major understanding of the construct of mental workload (fundamental breakthrough). It will provide human-centred designers with an interpretable and explainable model of MWL for real-time prediction of task performance, a revolutionary contribution to the field of Human-Computer Interaction (applied breakthrough). This contribution will allow human-centred designers to develop and rapidly test their interactive technologies and information-processing procedures aligned to the limitation of the mental capacity and that maximises human performance. The novelty of this research lies in the use of modern Deep Learning methods to automatically learn complex non-linear representations from multi-modal data, achieving the fundamental breakthrough. This will allow to move beyond the knowledge-driven research approaches that have produced hand-crafted deductive knowledge and dominated the research landscape on mental workload for 50 years. However, a challenging task is to translate these complex representations into human-interpretable forms, well-known issue in the field of Explainable Artificial Intelligence. To tackle this, modern methods for automatic rules extraction from deep-learning models will be employed, with symbolic argumentative reasoning methods, to bring these rules together in a highly accessible, explainable/interpretable model of mental workload, achieving the applied breakthrough.