Learning from label proportions in brain-computer interfaces: Online unsupervised learning with guarantees
Guardado en:
| Publicado en: | PLoS One vol. 12, no. 4 (Apr 2017), p. e0175856 |
|---|---|
| Autor principal: | |
| Otros Autores: | , , , , |
| Publicado: |
Public Library of Science
|
| Materias: | |
| Acceso en línea: | Citation/Abstract Full Text Full Text - PDF |
| Etiquetas: |
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 |