The paper discusses the potential of Deep Learning in extracting relevant information from raw EEG data. It highlights the challenge of processing EEG data from different experiments due to varying channel montages. The researchers suggest using spatial attention to harmonize these different channels, allowing for effective training of deep learning models. The model was tested on a gender classification task and it was revealed that spatial attention improved model performance. Furthermore, the model trained on data from different channel montages performed better than models trained on fixed channel data montages.
Publication date: 17 Oct 2023
Project Page: Not provided
Paper: https://arxiv.org/pdf/2310.10550
