Deep Riemannian Networks for EEG Decoding (2022)
Open in webOpen in zoteroOpen pdf
1 Abstract
State-of-the-art performance in electroencephalography (EEG) decoding tasks is currently often achieved with either Deep-Learning (DL) or Riemannian-Geometry-based decoders (RBDs). Recently, there is growing interest in Deep Riemannian Networks (DRNs) possibly combining the advantages of both previous classes of methods. However, there are still a range of topics where additional insight is needed to pave the way for a more widespread application of DRNs in EEG. These include, for example, robustness aspects of DRNs with EEG data, potential shortcuts DRNs could take with EEG data, and the relationship of DL with more traditional decoders, such as CSP.
2 NOTES
Zotero parent/PDF: 7V4Y8H8A / JL75XDBH (updated version S2V8ZWBU / URCWLT2Q). spdlearn implements this as EEGSPDNet.
Relevant Topics:
Quotes:
Quote
Quote here.