Computational Modeling of Social Cognition and associated Deficits by means of Artificial Neural Networks

Artificial Neural Networks (ANNs) are computer models that are loosely inspired by the functioning of the human brain. They are now the start of the art method for tackling a variety of AI problems, and are becoming an increasingly popular tool in neuroscientific studies. However, both domains pursue different goals: in AI model performance is key and brain resemblance is incidental, whilst in neuroscience the aim is chiefly to better understand the brain. A corollary is that despite a shared interest, both communities are organized in separate communities with little overlap. At KU Leuven, we find both sides represented in the inderdisciplinary institutes Leuven.AI and Leuven Brain Institute. The current proposal builds a bridge between both institutes and additionally puts forward two original focus points: the modeling of high-level tasks, in particular social cognition, as well as a focus on clinical conditions, in particular Autism Spectrum Disorder and Frontotemporal Dementia.

Keywords:Artificial Neural Networks, Neuroscience, Computational Psychiatry, Neurosymbolic AI, Frontotemporal Dementia, Autism Spectrum Disorder, Artificial Intelligence

Disciplines:Behavioural sciences, Group and interpersonal processes, Neuroimaging, Machine learning and decision making, Knowledge representation and reasoning