Data-Driven Modelling and Analysis of Attention-Working Memory Interplay
S.M. Ohkawa (TU Delft - Mechanical Engineering)
M. Jafarian – Mentor (TU Delft - Team Matin Jafarian)
D. Boskos – Graduation committee member (TU Delft - Team Dimitris Boskos)
M.L. van de Ruit – Graduation committee member (TU Delft - Biomechatronics & Human-Machine Control)
Saskia Haegens – Mentor
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
In this project, a data-driven modelling algorithm for learning new dynamical models from experimental magnetoencephalography (MEG) data is introduced. This algorithm provides a contrast to existing hypothesis-driven modelling techniques in neuronal dynamics, and is useful for generating new insights from data when hypotheses for the neural mechanisms underlying a process are not readily available. The algorithm utilises universal differential equations (UDEs), combining white-box modelling with machine learning techniques. The algorithm is applied to a single-subject human MEG dataset to produce an oscillator network model. The model captures the frequency-domain behaviour of and interaction between several brain regions of interest during completion of a working memory (WM) task. The machine learning techniques are used to identify the role of attention mechanisms in these interaction dynamics, providing neuroscientists with data-driven insights into the brain dynamics underlying the attention-WM interplay.