Compressing Subject-specific Brain-Computer Interface Models into One Model by Superposition in Hyperdimensional Space
- Conference Paper
Rights / licenseIn Copyright - Non-Commercial Use Permitted
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 , by 1.9×, and increases its accuracy by 2.41% (74.73% vs. 72.32%); (2) using a relatively larger Shallow ConvNet , our method achieves 2.95 x compression as well as 1.4% higher accuracy (75.05% vs. 73.59%). © 2020 EDAA. Show more
Book title2020 Design, Automation and Test in Europe Conference and Exhibition (DATE)
Pages / Article No.
SubjectHyperdimensional computing; Motor imagery; Convolutional Neural Networks
Organisational unit03996 - Benini, Luca / Benini, Luca
780215 - Computation-in-memory architecture based on resistive devices (EC)
NotesDue to the Corona virus (COVID-19) the conference was conducted virtually.
MoreShow all metadata