Deep learning for brain-signal decoding from electroencephalography

Abstract: Machine-learning systems can process larger amounts of brain signals and extract different information from the signals than humans, with potential uses in medical diagnosis or brain-computer interfaces. In particular, brain-signal decoding from electroencephalographic (EEG) recordings is a promising area for machine learning due to the relative ease of acquiring large amounts of EEG recordings and the difficulty of interpreting them manually. To decode EEG signals with machine learning, deep neural networks are a natural choice as they have been successful at a variety of natural-signal decoding tasks like object recognition from images or speech recognition from audio. However, prior to the work in this thesis, it was still unclear how well deep neural networks perform on EEG decoding compared to hand-engineered, feature-based approaches, and more research was needed to determine the optimal approaches for using deep learning to decode EEG. This thesis describes constructing and training deep neural networks for EEG decoding that perform at least as well as feature-based approaches. Visualizations presented in this thesis suggest that deep neural networks learn to extract both well-known physiologically plausible, as well as surprising EEG features

Angaben zum Objekt

• Standort: Deutsche Nationalbibliothek Frankfurt am Main
• Umfang: Online-Ressource
• Sprache: Englisch
• Anmerkungen: Universität Freiburg, Dissertation, 2024

Klassifikation und Themen

• Schlagwort: Elektroencephalogramm ; Merkmalsextraktion ; Elektroencephalographie ; Maschinelles Lernen ; Decodierung ; Gehirn-Computer-Schnittstelle ; Deep learning ; Elektroencephalogramm ; Elektroencephalographie ; Gehirn-Computer-Schnittstelle

Beteiligte, Orts- und Zeitangaben

• Ereignis: Veröffentlichung
• (wo): Freiburg
• (wer): Universität
• (wann): 2024
• Urheber: Schirrmeister, Robin Tibor
• Beteiligte Personen und Organisationen: Hutter, Frank ; Ball, Tonio ; Hutter, Frank ; Ball, Tonio ; Albert-Ludwigs-Universität Freiburg. Fakultät für Angewandte Wissenschaften ; Maschinelles Lernen und Natürlichsprachliche Systeme, Professur Frank Hutter

Weitere Informationen

• DOI: 10.6094/UNIFR/242967
• URN: urn:nbn:de:bsz:25-freidok-2429670
• Rechteinformation: Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
• Letzte Aktualisierung: 25.03.2025, 13:45 MEZ