Domain Adaptation and Transfer Learning methods enhance Deep Learning Models used in Inner Speech Based Brain Computer Interfaces

Brain Computer Interfaces are useful devices that can partially restore the communication from severe compromised patients. Although the advances in deep learning have significantly improved brain pattern recognition, a large amount of data is required for training these deep architectures. In the l...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Zablocki, Luciano Ivan, Mendoza, Agustín Nicolás, Nieto, Nicolás
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2022
Materias:
Ciencias Informáticas
Deep Learning
Domain Adaptation
Transfer Learning
Convolutional Neural Network
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/151632
https://publicaciones.sadio.org.ar/index.php/JAIIO/article/download/263/214
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-151632
record_format dspace
spelling I19-R120-10915-1516322023-05-03T20:02:12Z http://sedici.unlp.edu.ar/handle/10915/151632 https://publicaciones.sadio.org.ar/index.php/JAIIO/article/download/263/214 issn:2451-7496 Domain Adaptation and Transfer Learning methods enhance Deep Learning Models used in Inner Speech Based Brain Computer Interfaces Zablocki, Luciano Ivan Mendoza, Agustín Nicolás Nieto, Nicolás 2022-10 2022 2023-04-18T14:52:32Z en Ciencias Informáticas Deep Learning Domain Adaptation Transfer Learning Convolutional Neural Network Brain Computer Interfaces are useful devices that can partially restore the communication from severe compromised patients. Although the advances in deep learning have significantly improved brain pattern recognition, a large amount of data is required for training these deep architectures. In the last years, the inner speech paradigm has drew much attention, as it can potentially allow a natural control of different devices. However, as of the date of this publication, there is only a small amount of data available in this paradigm. In this work we show that it is possible, by means of transfer learning and domain adaptation methods, to make the most of the scarce data, enhancing the training process of a deep learning architecture used in brain computer interfaces. Sociedad Argentina de Informática e Investigación Operativa Objeto de conferencia Objeto de conferencia http://creativecommons.org/licenses/by-nc-sa/4.0/ Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) application/pdf 54-60
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
Deep Learning
Domain Adaptation
Transfer Learning
Convolutional Neural Network
spellingShingle Ciencias Informáticas
Deep Learning
Domain Adaptation
Transfer Learning
Convolutional Neural Network
Zablocki, Luciano Ivan
Mendoza, Agustín Nicolás
Nieto, Nicolás
Domain Adaptation and Transfer Learning methods enhance Deep Learning Models used in Inner Speech Based Brain Computer Interfaces
topic_facet Ciencias Informáticas
Deep Learning
Domain Adaptation
Transfer Learning
Convolutional Neural Network
description Brain Computer Interfaces are useful devices that can partially restore the communication from severe compromised patients. Although the advances in deep learning have significantly improved brain pattern recognition, a large amount of data is required for training these deep architectures. In the last years, the inner speech paradigm has drew much attention, as it can potentially allow a natural control of different devices. However, as of the date of this publication, there is only a small amount of data available in this paradigm. In this work we show that it is possible, by means of transfer learning and domain adaptation methods, to make the most of the scarce data, enhancing the training process of a deep learning architecture used in brain computer interfaces.
format Objeto de conferencia
Objeto de conferencia
author Zablocki, Luciano Ivan
Mendoza, Agustín Nicolás
Nieto, Nicolás
author_facet Zablocki, Luciano Ivan
Mendoza, Agustín Nicolás
Nieto, Nicolás
author_sort Zablocki, Luciano Ivan
title Domain Adaptation and Transfer Learning methods enhance Deep Learning Models used in Inner Speech Based Brain Computer Interfaces
title_short Domain Adaptation and Transfer Learning methods enhance Deep Learning Models used in Inner Speech Based Brain Computer Interfaces
title_full Domain Adaptation and Transfer Learning methods enhance Deep Learning Models used in Inner Speech Based Brain Computer Interfaces
title_fullStr Domain Adaptation and Transfer Learning methods enhance Deep Learning Models used in Inner Speech Based Brain Computer Interfaces
title_full_unstemmed Domain Adaptation and Transfer Learning methods enhance Deep Learning Models used in Inner Speech Based Brain Computer Interfaces
title_sort domain adaptation and transfer learning methods enhance deep learning models used in inner speech based brain computer interfaces
publishDate 2022
url http://sedici.unlp.edu.ar/handle/10915/151632
https://publicaciones.sadio.org.ar/index.php/JAIIO/article/download/263/214
work_keys_str_mv AT zablockilucianoivan domainadaptationandtransferlearningmethodsenhancedeeplearningmodelsusedininnerspeechbasedbraincomputerinterfaces
AT mendozaagustinnicolas domainadaptationandtransferlearningmethodsenhancedeeplearningmodelsusedininnerspeechbasedbraincomputerinterfaces
AT nietonicolas domainadaptationandtransferlearningmethodsenhancedeeplearningmodelsusedininnerspeechbasedbraincomputerinterfaces
_version_ 1765659993230540800

Ejemplares similares