Deep Invertible Networks for EEG-based brain-signal decoding
arXiv:1907.07746v1
Originality Synthesis-oriented
AI Analysis
This work addresses brain-signal decoding for EEG analysis, but it appears incremental as it builds on existing methods with limited concrete improvements.
The paper tackled EEG-based brain signal decoding using deep invertible networks, finding they generate realistic EEG signals and classify novel signals above chance, with discussions on regularization for better accuracies.
In this manuscript, we investigate deep invertible networks for EEG-based brain signal decoding and find them to generate realistic EEG signals as well as classify novel signals above chance. Further ideas for their regularization towards better decoding accuracies are discussed.