Objective.Functional specialization is fundamental to neural information processing. Here, we study whether and how functional specialization emerges in artificial deep convolutional neural networks (CNNs) during a brain-computer interfacing (BCI) task.Approach.We trained CNNs to predict hand movement speed from intracranial electroencephalography (iEEG) and delineated how units across the different CNN hidden layers learned to represent the iEEG signal.Main results.We show that distinct, functionally interpretable neural populations emerged as a result of the training process. While some units became sensitive to either iEEG amplitude or phase, others showed bimodal behavior with significant sensitivity to both features. Pruning of highly sensitive units resulted in a steep drop of decoding accuracy not observed for pruning of less sensitive units, highlighting the functional relevance of the amplitude- and phase-specialized populations.Significance.We anticipate that emergent functional specialization as uncovered here will become a key concept in research towards interpretable deep learning for neuroscience and BCI applications.

Department of Neurology 2nd Faculty of Medicine Charles University and Motol University Hospital Prague Czech Republic

Epilepsy Center Department of Neurosurgery Medical Center University of Freiburg Faculty of Medicine University of Freiburg Freiburg Germany

Machine Learning Lab Department of Computer Science Faculty of Engineering University of Freiburg Freiburg Germany

Neuromedical AI Lab Department of Neurosurgery Medical Center University of Freiburg Faculty of Medicine University of Freiburg Freiburg Germany

References provided by Crossref.org

Antagonistic behavior of brain networks mediated by low-frequency oscillations: electrophysiological dynamics during internal-external attention switching