Skip to main content

Using EEG-based images to predict autism early

Venue: Online

Developing digital biomarkers that would enable reliable detection of autism–ASD early in life is challenging because of the variability in the presentation of the autistic disorder and the need for collecting simple measurements routinely during check-ups.

This talk by Birkbeck PhD researcher Cosmin Stamate shows that considering Electroencephalogram (EEG)-as-an-image and using end-to-end deep learning is a viable way of extracting useful digital biomarkers from EEG measurements for predicting autism in infants.

Online session

This event will take place online on Microsoft Teams. Pre-event information and joining links will be emailed to you before the session. Please ensure you book your place via the link above to receive the joining instructions.


Cosmin Stamate has an MSc in Intelligent Technologies from Birkbeck, University of London where he took a particular interest in artificial neural networks, evolutionary algorithms and transfer learning between heterogeneous tasks using artificial neural networks. Some of his industry roles include data analyst (on a consulting basis) for Tesco and Schroders and other healthcare startups. Currently, he is working towards a hybrid PhD that bridges research at the Birkbeck Knowledge Lab, Department of Computer Science and the Department of Psychological Sciences at Birkbeck; the PhD is focused on developing novel deep learning algorithms with the help of population and cognitive genetics studies.

He is an active member of the Birkbeck Knowledge Lab, Centre for Brain & Cognitive Development, Birkbeck Babylab, Comparative Cognition Group and Me, Human where he applies state of the art machine learning on high dimensional data (EEG, fNIRS, smartphone sensors, etc.).

Contact name: