13
IRUS Total
Downloads
  Altmetric

2021 BEETL competition: advancing transfer learning for subject independence & heterogenous EEG data sets

File Description SizeFormat 
Wei21a.pdfPublished version990.66 kBAdobe PDFView/Open
Title: 2021 BEETL competition: advancing transfer learning for subject independence & heterogenous EEG data sets
Authors: Wei, X
Faisal, AA
Grosse-Wentrup, M
Gramfort, A
Chevallier, S
Jayaram, V
Jeunet, C
Bakas, S
Ludwig, S
Barmpas, K
Bahri, M
Panagakis, Y
Laskaris, N
Adamos, DA
Zafeiriou, S
Duong, WC
Gordon, SM
Lawhern, VJ
Śliwowski, M
Rouanne, V
Tempczyk, P
Item Type: Conference Paper
Abstract: Transfer learning and meta-learning offer some of the most promising avenues to unlock the scalability of healthcare and consumer technologies driven by biosignal data. This is because regular machine learning methods cannot generalise well across human subjects and handle learning from different, heterogeneously collected data sets, thus limiting the scale of training data available. On the other hand, the many developments in transfer- and meta-learning fields would benefit significantly from a real-world benchmark with immediate practical application. Therefore, we pick electroencephalography (EEG) as an exemplar for all the things that make biosignal data analysis a hard problem. We design two transfer learning challenges around a. clinical diagnostics and b. neurotechnology. These two challenges are designed to probe algorithmic performance with all the challenges of biosignal data, such as low signal-to-noise ratios, major variability among subjects, differences in the data recording sessions and techniques, and even between the specific BCI tasks recorded in the dataset. Task 1 is centred on the field of medical diagnostics, addressing automatic sleep stage annotation across subjects. Task 2 is centred on Brain-Computer Interfacing (BCI), addressing motor imagery decoding across both subjects and data sets. The successful 2021 BEETL competition with its over 30 competing teams and its 3 winning entries brought attention to the potential of deep transfer learning and combinations of set theory and conventional machine learning techniques to overcome the challenges. The results set a new state-of-the-art for the real-world BEETL benchmarks.
Issue Date: 22-Nov-2022
Date of Acceptance: 10-Apr-2022
URI: http://hdl.handle.net/10044/1/101137
Publisher: PMLR
Start Page: 1
End Page: 16
Journal / Book Title: Proceedings of Machine Learning Research
Copyright Statement: © 2022 X. Wei et al.
Conference Name: NeurIPS 2021 Competitions and Demonstrations Track, Proceedings of Machine Learning Research
Publication Status: Published
Start Date: 2021-12-13
Finish Date: 2021-12-14
Conference Place: Virtual event
Online Publication Date: 2022-11-22
Appears in Collections:Bioengineering
Computing