Intracranial Error Detection via Deep Learning Thanks: This work was supported by DFG grant EXC1086 BrainLinks-BrainTools, Baden-Württemberg Stiftung grant BMI-Bot, Graduate School of Robotics in Freiburg, Germany and the State Graduate Funding Program of Baden-Württemberg, Germany.
Martin Völker Affiliation: Graduate School of Robotics Albert-Ludwigs-University Freiburg, Germany Jiří Hammer Affiliation: Department of Neurology Motol University Hospital, Charles University Prague, Czech Republic Robin T. Schirrmeister Affiliation: Translational Neurotechnology Lab University Medical Center Freiburg Freiburg, Germany Joos Behncke Affiliation: Department of Computer Science Albert-Ludwigs-University Freiburg, Germany Lukas D.J. Fiederer Affiliation: Faculty of Biology Albert-Ludwigs-University Freiburg, Germany Andreas Schulze-Bonhage Affiliation: Epilepsy Center University Medical Center Freiburg Freiburg, Germany Petr Marusič Affiliation: Department of Neurology Motol University Hospital, Charles University Prague, Czech Republic Wolfram Burgard Affiliation: Department of Computer Science Albert-Ludwigs-University Freiburg, Germany Tonio Ball Affiliation: Translational Neurotechnology Lab University Medical Center Freiburg Freiburg, Germany
Abstract
Deep learning techniques have revolutionized the field of machine learning and were recently successfully applied to various classification problems in noninvasive electroencephalography (EEG). However, these methods were so far only rarely evaluated for use in intracranial EEG. We employed convolutional neural networks (CNNs) to classify and characterize the error-related brain response as measured in 24 intracranial EEG recordings. Decoding accuracies of CNNs were significantly higher than those of a regularized linear discriminant analysis. Using time-resolved deep decoding, it was possible to classify errors in various regions in the human brain, and further to decode errors over 200 ms before the actual erroneous button press, e.g., in the precentral gyrus. Moreover, deeper networks performed better than shallower networks in distinguishing correct from error trials in all-channel decoding. In single recordings, up to 100 % decoding accuracy was achieved. Visualization of the networks’ learned features indicated that multivariate decoding on an ensemble of channels yields related, albeit non-redundant information compared to single-channel decoding. In summary, here we show th
原文 arXiv:1805.01667;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1805.01667v3