Imperial College London
Portrait Picture

Professor Aldo Faisal

Faculty of Engineering, Department of Bioengineering

Professor of AI & Neuroscience
 
 
 
//

Contact

 

+44 (0)20 7594 6373a.faisal Website

 
 
//

Assistant

 

Miss Teresa Ng +44 (0)20 7594 8300

 
//

Location

 

4.08Royal School of MinesSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Wei:2022,
author = {Wei, X and Faisal, AA and Grosse-Wentrup, M and Gramfort, A and Chevallier, S and Jayaram, V and Jeunet, C and Bakas, S and Ludwig, S and Barmpas, K and Bahri, M and Panagakis, Y and Laskaris, N and Adamos, DA and Zafeiriou, S and Duong, WC and Gordon, SM and Lawhern, VJ and liwowski, M and Rouanne, V and Tempczyk, P},
pages = {1--16},
publisher = {PMLR},
title = {2021 BEETL competition: advancing transfer learning for subject independence and heterogenous EEG data sets},
url = {https://proceedings.mlr.press/v176/wei22a.html},
year = {2022}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - 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.
AU  - Wei,X
AU  - Faisal,AA
AU  - Grosse-Wentrup,M
AU  - Gramfort,A
AU  - Chevallier,S
AU  - Jayaram,V
AU  - Jeunet,C
AU  - Bakas,S
AU  - Ludwig,S
AU  - Barmpas,K
AU  - Bahri,M
AU  - Panagakis,Y
AU  - Laskaris,N
AU  - Adamos,DA
AU  - Zafeiriou,S
AU  - Duong,WC
AU  - Gordon,SM
AU  - Lawhern,VJ
AU  - liwowski,M
AU  - Rouanne,V
AU  - Tempczyk,P
EP  - 16
PB  - PMLR
PY  - 2022///
SP  - 1
TI  - 2021 BEETL competition: advancing transfer learning for subject independence and heterogenous EEG data sets
UR  - https://proceedings.mlr.press/v176/wei22a.html
UR  - http://hdl.handle.net/10044/1/101137
ER  -
Download