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

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 classifi...

Descripción completa

Detalles Bibliográficos
Autores principales: Hübner, David, Verhoeven, Thibault, Schmid, Konstantin, Müller, Klaus-Robert, Tangermann, Michael, Kindermans, Pieter-Jan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2017
Materias:
Research Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5391120/
https://www.ncbi.nlm.nih.gov/pubmed/28407016
http://dx.doi.org/10.1371/journal.pone.0175856

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5391120/
https://www.ncbi.nlm.nih.gov/pubmed/28407016
http://dx.doi.org/10.1371/journal.pone.0175856

Ejemplares similares