1. Compressing Subject-specific Brain-Computer Interface Models into One Model by Superposition in Hyperdimensional Space
- Author
-
Hersche, Michael, Rupp, Philipp, Benini, Luca, Rahimi, Abbas, Hersche M., Rupp P., Benini L., and Rahimi A.
- Subjects
010302 applied physics ,business.industry ,Computer science ,Deep learning ,Convolutional Neural Networks ,Pattern recognition ,02 engineering and technology ,01 natural sciences ,Convolutional neural network ,020202 computer hardware & architecture ,Multiclass classification ,Superposition principle ,Motor imagery ,Compression (functional analysis) ,0103 physical sciences ,0202 electrical engineering, electronic engineering, information engineering ,EEG, motor imagery brain-computer interfaces (MI-BCIs) ,Artificial intelligence ,Hyperdimensional computing ,business ,Brain–computer interface - Abstract
Accurate multiclass classification of electroencephalography (EEG) signals is still a challenging task towards the development of reliable motor imagery brain-computer interfaces (MI-BCIs). Deep learning algorithms have been recently used in this area to deliver a compact and accurate model. Reaching high-level of accuracy requires to store subjects-specific trained models that cannot be achieved with an otherwise compact model trained globally across all subjects. In this paper, we propose a new methodology that closes the gap between these two extreme modeling approaches: we reduce the overall storage requirements by superimposing many subject-specific models into one single model such that it can be reliably decomposed, after retraining, to its constituent models while providing a trade-off between compression ratio and accuracy. Our method makes the use of unexploited capacity of trained models by orthogonalizing parameters in a hyperdimensional space, followed by iterative retraining to compensate noisy decomposition. This method can be applied to various layers of deep inference models. Experimental results on the 4-class BCI competition IV-2a dataset show that our method exploits unutilized capacity for compression and surpasses the accuracy of two state-of-the-art networks: (1) it compresses the smallest network, EEGNet [1], by 1.9×, and increases its accuracy by 2.41% (74.73% vs. 72.32%); (2) using a relatively larger Shallow ConvNet [2], our method achieves 2.95 x compression as well as 1.4% higher accuracy (75.05% vs. 73.59%). © 2020 EDAA., 2020 Design, Automation and Test in Europe Conference and Exhibition (DATE), ISBN:978-3-9819263-4-7, ISBN:978-1-7281-4468-9
- Published
- 2020