Learning from label proportions in brain-computer interfaces: Online unsupervised learning with guarantees

Guardado en:
Detalles Bibliográficos
Publicado en:PLoS One vol. 12, no. 4 (Apr 2017), p. e0175856
Autor principal: Hübner, David
Otros Autores: Verhoeven, Thibault, Schmid, Konstantin, Klaus-Robert Müller, Tangermann, Michael, Pieter-Jan Kindermans
Publicado:
Public Library of Science
Materias:
Acceso en línea:Citation/Abstract
Full Text
Full Text - PDF
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!

MARC

LEADER 00000nab a2200000uu 4500
001 1887374509
003 UK-CbPIL
022 |a 1932-6203 
024 7 |a 10.1371/journal.pone.0175856  |2 doi 
035 |a 1887374509 
045 2 |b d20170401  |b d20170430 
084 |a 174835  |2 nlm 
100 1 |a Hübner, David 
245 1 |a Learning from label proportions in brain-computer interfaces: Online unsupervised learning with guarantees 
260 |b Public Library of Science  |c Apr 2017 
513 |a Journal Article 
520 3 |a Objective Using traditional approaches, a brain-computer interface (BCI) requires the collection of calibration data for new subjects prior to online use. Calibration time can be reduced or eliminated e.g., by subject-to-subject transfer of a pre-trained classifier or unsupervised adaptive classification methods which learn from scratch and adapt over time. While such heuristics work well in practice, none of them can provide theoretical guarantees. Our objective is to modify an event-related potential (ERP) paradigm to work in unison with the machine learning decoder, and thus to achieve a reliable unsupervised calibrationless decoding with a guarantee to recover the true class means. Method We introduce learning from label proportions (LLP) to the BCI community as a new unsupervised, and easy-to-implement classification approach for ERP-based BCIs. The LLP estimates the mean target and non-target responses based on known proportions of these two classes in different groups of the data. We present a visual ERP speller to meet the requirements of LLP. For evaluation, we ran simulations on artificially created data sets and conducted an online BCI study with 13 subjects performing a copy-spelling task. Results Theoretical considerations show that LLP is guaranteed to minimize the loss function similar to a corresponding supervised classifier. LLP performed well in simulations and in the online application, where 84.5% of characters were spelled correctly on average without prior calibration. Significance The continuously adapting LLP classifier is the first unsupervised decoder for ERP BCIs guaranteed to find the optimal decoder. This makes it an ideal solution to avoid tedious calibration sessions. Additionally, LLP works on complementary principles compared to existing unsupervised methods, opening the door for their further enhancement when combined with LLP. 
651 4 |a Germany 
651 4 |a Berlin Germany 
653 |a Social 
653 |a Brain 
653 |a Men 
653 |a Visual perception 
653 |a Computer science 
653 |a Brain research 
653 |a Calibration 
653 |a Implants 
653 |a Computer applications 
653 |a Electroencephalography 
653 |a Learning algorithms 
653 |a Data processing 
653 |a Multivariate analysis 
653 |a Classification 
653 |a Neural networks 
653 |a Problem solving 
653 |a Event-related potentials 
653 |a Engineering 
653 |a Algorithms 
653 |a Paradigms 
653 |a Women 
653 |a Internet 
653 |a Artificial intelligence 
653 |a Decoding 
653 |a Unsupervised learning 
653 |a Machine learning 
653 |a Human-computer interface 
653 |a Classifiers 
700 1 |a Verhoeven, Thibault 
700 1 |a Schmid, Konstantin 
700 1 |a Klaus-Robert Müller 
700 1 |a Tangermann, Michael 
700 1 |a Pieter-Jan Kindermans 
773 0 |t PLoS One  |g vol. 12, no. 4 (Apr 2017), p. e0175856 
786 0 |d ProQuest  |t Health & Medical Collection 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/1887374509/abstract/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full Text  |u https://www.proquest.com/docview/1887374509/fulltext/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/1887374509/fulltextPDF/embedded/L8HZQI7Z43R0LA5T?source=fedsrch