neuroscience · supervision

Thesis supervision | Gagandeep Singh: EEG Source Localization: A Machine Learning Approach

EEG source localization is hard. The current state of the art is beamforming. We took a simultaneous EEG-fMRI dataset, used fMRI to find the true source and measured how well a beamformer can predict the Brodmann area where the activity is. It turned out that it could not (random prediction level). Gagandeep then developed an approach based on autoencoders that achieved higher-than-random classification ability.

Download PDF