TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Mind reading with regularized multinomial logistic regression

Tutkimustuotosvertaisarvioitu

Standard

Mind reading with regularized multinomial logistic regression. / Huttunen, Heikki; Manninen, Tapio; Kauppi, Jukka-Pekka; Tohka, Jussi.

julkaisussa: Machine Vision and Applications, Vuosikerta 24, Nro 6, 2013, s. 1311-1325.

Tutkimustuotosvertaisarvioitu

Harvard

Huttunen, H, Manninen, T, Kauppi, J-P & Tohka, J 2013, 'Mind reading with regularized multinomial logistic regression', Machine Vision and Applications, Vuosikerta. 24, Nro 6, Sivut 1311-1325. https://doi.org/10.1007/s00138-012-0464-y

APA

Huttunen, H., Manninen, T., Kauppi, J-P., & Tohka, J. (2013). Mind reading with regularized multinomial logistic regression. Machine Vision and Applications, 24(6), 1311-1325. https://doi.org/10.1007/s00138-012-0464-y

Vancouver

Huttunen H, Manninen T, Kauppi J-P, Tohka J. Mind reading with regularized multinomial logistic regression. Machine Vision and Applications. 2013;24(6):1311-1325. https://doi.org/10.1007/s00138-012-0464-y

Author

Huttunen, Heikki ; Manninen, Tapio ; Kauppi, Jukka-Pekka ; Tohka, Jussi. / Mind reading with regularized multinomial logistic regression. Julkaisussa: Machine Vision and Applications. 2013 ; Vuosikerta 24, Nro 6. Sivut 1311-1325.

Bibtex - Lataa

@article{8ee48ea88be8480196c3a58f87ebff51,
title = "Mind reading with regularized multinomial logistic regression",
abstract = "In this paper, we consider the problem of multinomial classification of magnetoencephalography (MEG) data. The proposed method participated in the MEG mind reading competition of ICANN'11 conference, where the goal was to train a classifier for predicting the movie the test person was shown. Our approach was the best among 10 submissions, reaching accuracy of 68 {\%} of correct classifications in this five category problem. The method is based on a regularized logistic regression model, whose efficient feature selection is critical for cases with more measurements than samples. Moreover, a special attention is paid to the estimation of the generalization error in order to avoid overfitting to the training data. Here, in addition to describing our competition entry in detail, we report selected additional experiments, which question the usefulness of complex feature extraction procedures and the basic frequency decomposition of MEG signal for this application.",
author = "Heikki Huttunen and Tapio Manninen and Jukka-Pekka Kauppi and Jussi Tohka",
note = "Online first<br/>Contribution: organisation=sgn,FACT1=1<br/>Publisher name: Springer-Verlag",
year = "2013",
doi = "10.1007/s00138-012-0464-y",
language = "English",
volume = "24",
pages = "1311--1325",
journal = "Machine Vision and Applications",
issn = "0932-8092",
publisher = "Springer",
number = "6",

}

RIS (suitable for import to EndNote) - Lataa

TY - JOUR

T1 - Mind reading with regularized multinomial logistic regression

AU - Huttunen, Heikki

AU - Manninen, Tapio

AU - Kauppi, Jukka-Pekka

AU - Tohka, Jussi

N1 - Online first<br/>Contribution: organisation=sgn,FACT1=1<br/>Publisher name: Springer-Verlag

PY - 2013

Y1 - 2013

N2 - In this paper, we consider the problem of multinomial classification of magnetoencephalography (MEG) data. The proposed method participated in the MEG mind reading competition of ICANN'11 conference, where the goal was to train a classifier for predicting the movie the test person was shown. Our approach was the best among 10 submissions, reaching accuracy of 68 % of correct classifications in this five category problem. The method is based on a regularized logistic regression model, whose efficient feature selection is critical for cases with more measurements than samples. Moreover, a special attention is paid to the estimation of the generalization error in order to avoid overfitting to the training data. Here, in addition to describing our competition entry in detail, we report selected additional experiments, which question the usefulness of complex feature extraction procedures and the basic frequency decomposition of MEG signal for this application.

AB - In this paper, we consider the problem of multinomial classification of magnetoencephalography (MEG) data. The proposed method participated in the MEG mind reading competition of ICANN'11 conference, where the goal was to train a classifier for predicting the movie the test person was shown. Our approach was the best among 10 submissions, reaching accuracy of 68 % of correct classifications in this five category problem. The method is based on a regularized logistic regression model, whose efficient feature selection is critical for cases with more measurements than samples. Moreover, a special attention is paid to the estimation of the generalization error in order to avoid overfitting to the training data. Here, in addition to describing our competition entry in detail, we report selected additional experiments, which question the usefulness of complex feature extraction procedures and the basic frequency decomposition of MEG signal for this application.

U2 - 10.1007/s00138-012-0464-y

DO - 10.1007/s00138-012-0464-y

M3 - Article

VL - 24

SP - 1311

EP - 1325

JO - Machine Vision and Applications

JF - Machine Vision and Applications

SN - 0932-8092

IS - 6

ER -