Show simple item record

dc.contributor.author
Hersche, Michael
dc.contributor.author
Rupp, Philipp
dc.contributor.author
Benini, Luca
dc.contributor.author
Rahimi, Abbas
dc.date.accessioned
2020-01-06T12:37:24Z
dc.date.available
2019-12-23T20:19:44Z
dc.date.available
2020-01-06T12:37:24Z
dc.date.issued
2020
dc.identifier.uri
http://hdl.handle.net/20.500.11850/387117
dc.identifier.doi
10.3929/ethz-b-000387117
dc.description.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, by 1.9x, and increases its accuracy by 2.41% (74.73% vs. 72.32%); (2) using a relatively larger Shallow ConvNet, our method achieves 2.95x compression as well as 1.4% higher accuracy (75.05% vs. 73.59%).
en_US
dc.format
application/pdf
en_US
dc.language.iso
en
en_US
dc.rights.uri
http://rightsstatements.org/page/InC-NC/1.0/
dc.subject
Hyperdimensional computing
en_US
dc.subject
Motor imagery
en_US
dc.subject
Convolutional Neural Networks
en_US
dc.title
Compressing Subject-specific Brain–Computer Interface Models into One Model by Superposition in Hyperdimensional Space
en_US
dc.type
Conference Paper
dc.rights.license
In Copyright - Non-Commercial Use Permitted
ethz.size
6 p. accepted version
en_US
ethz.version.deposit
acceptedVersion
en_US
ethz.event
Design, Automation and Test in Europe (DATE 2020)
en_US
ethz.event.location
Grenoble, France
en_US
ethz.event.date
March 9-13, 2020
en_US
ethz.notes
Conference lecture to be held on March 10, 2020
en_US
ethz.grant
Computation-in-memory architecture based on resistive devices
en_US
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02140 - Dep. Inf.technologie und Elektrotechnik / Dep. of Inform.Technol. Electrical Eng.::02636 - Institut für Integrierte Systeme / Integrated Systems Laboratory::03996 - Benini, Luca / Benini, Luca
en_US
ethz.leitzahl.certified
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02140 - Dep. Inf.technologie und Elektrotechnik / Dep. of Inform.Technol. Electrical Eng.::02636 - Institut für Integrierte Systeme / Integrated Systems Laboratory::03996 - Benini, Luca / Benini, Luca
en_US
ethz.grant.agreementno
780215
ethz.grant.agreementno
780215
ethz.grant.fundername
EC
ethz.grant.fundername
EC
ethz.grant.funderDoi
10.13039/501100000780
ethz.grant.funderDoi
10.13039/501100000780
ethz.grant.program
H2020
ethz.grant.program
H2020
ethz.date.deposited
2019-12-23T20:20:03Z
ethz.source
FORM
ethz.eth
yes
en_US
ethz.availability
Open access
en_US
ethz.rosetta.exportRequired
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Compressing%20Subject-specific%20Brain%E2%80%93Computer%20Interface%20Models%20into%20One%20Model%20by%20Superposition%20in%20Hyperdimensional%20Space&rft.date=2020&rft.au=Hersche,%20Michael&Rupp,%20Philipp&Benini,%20Luca&Rahimi,%20Abbas&rft.genre=proceeding&rft.btitle=Compressing%20Subject-specific%20Brain%E2%80%93Computer%20Interface%20Models%20into%20One%20Model%20by%20Superposition%20in%20Hyperdimensional%20Space
 Search via SFX

Files in this item

Thumbnail

Publication type

Show simple item record