Learning Topology-Agnostic EEG Representations with Geometry-Aware Modeling
Dec 10, 2023
Speakers
Yansen Wang
Speaker · 0 followers
Dongsheng Li
Speaker · 0 followers
About
Large-scale pre-training has shown great potential to enhance the models on the downstream task in vision and language. Developing similar techniques for scalp electroencephalogram (EEG) is suitable since unlabelled data is plentiful. Meanwhile, various sampling channels selection and inherent structural and spatial information bring challenges and avenues to improve existing pre-training strategies further. In order to break the boundaries between different EEG resources and facilitate cross-dataset EEG pre-training, we propose to map all kinds of channel selections to a unified topology. We further introduce **MMM**, a pre-training framework with **M**ulti-dimensional position encoding,**M**ulti-level channel hierarchy, **M**ulti-stage pre-training strategy built on the unified topology to obtain topology-agnostic representations. Experiments demonstrate that our approach yields impressive improvements over previous state-of-the-art techniques on emotional recognition benchmark datasets.Large-scale pre-training has shown great potential to enhance the models on the downstream task in vision and language. Developing similar techniques for scalp electroencephalogram (EEG) is suitable since unlabelled data is plentiful. Meanwhile, various sampling channels selection and inherent structural and spatial information bring challenges and avenues to improve existing pre-training strategies further. In order to break the boundaries between different EEG resources and facilitate cross-da…
Organizer
NeurIPS 2023
Account · 622 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Guiding The Last Layer in Federated Learning with Pre-Trained Models
Watch later
Gwen Legate, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Tree of Thoughts: Deliberate Problem Solving with Large Language Models
Watch later
Shunyu Yao, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Learn to Forecast Heterogeneous Dynamics
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Introducing our evaluation metric
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Statistical Limits of Adaptive Linear Models: Low-Dimensional Estimation and Inference
Watch later
Licong Lin, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
FAIR-Ensemble: Homogeneous Deep Ensembling Naturally Attenuates Disparate Group Performances
Watch later
Wei-Yin Ko, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%