End-to-end learnable EEG channel selection for deep neural networks with Gumbel-softmax
- 20 July 2021
- journal article
- research article
- Published by IOP Publishing in Journal of Neural Engineering
- Vol. 18 (4) , 0460a9
Abstract
Objective. To develop an efficient, embedded electroencephalogram (EEG) channel selection approach for deep neural networks, allowing us to match the channel selection to the target model, while avoiding the large computational burdens of wrapper approaches in conjunction with neural networks. Approach. We employ a concrete selector layer to jointly optimize the EEG channel selection and network parameters. This layer uses a Gumbel-softmax trick to build continuous relaxations of the discrete parameters involved in the selection process, allowing them be learned in an end-to-end manner with traditional backpropagation. As the selection layer was often observed to include the same channel twice in a certain selection, we propose a regularization function to mitigate this behavior. We validate this method on two different EEG tasks: motor execution and auditory attention decoding. For each task, we compare the performance of the Gumbel-softmax method with a baseline EEG channel selection approach tailored towards this specific task: mutual information and greedy forward selection with the utility metric respectively. Main results. Our experiments show that the proposed framework is generally applicable, while performing at least as well as (and often better than) these state-of-the-art, task-specific approaches. Significance. The proposed method offers an efficient, task- and model-independent approach to jointly learn the optimal EEG channels along with the neural network weights.Keywords
All Related Versions
Funding Information
- Fonds Wetenschappelijk Onderzoek (G.0A49.18N)
- H2020 European Research Council (802895)
This publication has 18 references indexed in Scilit:
- Complexity Analysis of Neonatal EEG Using Multiscale Entropy: Applications in Brain Maturation and Sleep Stage ClassificationEntropy, 2017
- Deep learning with convolutional neural networks for EEG decoding and visualizationHuman Brain Mapping, 2017
- Group sparse regularization for deep neural networksNeurocomputing, 2017
- Improved SFFS method for channel selection in motor imagery based BCINeurocomputing, 2016
- Auditory-Inspired Speech Envelope Extraction Methods for Improved EEG-Based Auditory Attention Detection in a Cocktail Party ScenarioIEEE Transactions on Neural Systems and Rehabilitation Engineering, 2016
- Heterogeneous Feature Selection With Multi-Modal Deep Neural Networks and Sparse Group LASSOIEEE Transactions on Multimedia, 2015
- Decoding the attended speech stream with multi-channel EEG: implications for online, daily-life applicationsJournal of Neural Engineering, 2015
- Distributed Signal Processing for Wireless EEG Sensor NetworksIEEE Transactions on Neural Systems and Rehabilitation Engineering, 2015
- Disorders of consciousness after acquired brain injury: the state of the scienceNature Reviews Neurology, 2014
- Wearable ElectroencephalographyIEEE Engineering in Medicine and Biology Magazine, 2010