Cognitive Computational Neuroscience

Research

Our research uses computational and machine learning techniques to study functions of the human brain in health and disease. Our work focuses on three main axes:



Auditory processing and predictions

Intrinsic timescales in the auditory system Figure from: Cusinato, Alnes et al., 2023

The world around us is full of rich sensory experiences, which often follow repetitive rules. Environmental regularities can help us learn patterns from our environment and form predictions about future events before these occur.

To shed light into the neural mechanisms that support processing of environmental stimuli and the formation of predictions about future events, we are using scalp and intracranial electroencephalography (EEG, iEEG), in combination with computational modeling techniques.

Representative publications



Neural functions in coma and sleep

Graphical Abstract Alnes et al., 2021 Figure from Alnes et al., 2021, Neuroimage

When consciousness fades away we are not aware of our surroundings. However, our brains continue to process information from the environment, like sounds.
In our work, we are investigating how the human brain responds to stimuli of the environment when consciousness is lost. Moreover, we are combining electrophysiological measurements of brain activity with computational techniques, like measures of neural synchrony and complexity, or deep learning algorithms, to identify predictors of awakening from a coma.

Representative publications



Machine learning algorithms for neuroscience

Deep learning pipeline Figure adapted from: Aellen et al., 2023

As the amount of data in the field of neuroscience and neurology increases, it becomes imperative to have powerful algorithms for analysing them. Machine learning algorithms have revolutionized several fields, but their use in electrophysiological data remains limited. In our work, we are developing deep learning pipelines for analysing electrophysiological data, with emphasis on interpretability, and clinical applications, such as predicting outcome from post anoxic coma. Moreover, we are evaluating the effects of algorithmic bias when applying machine learning techniques on medical data.

Representative publications