Header

UZH-Logo

Maintenance Infos

Model-based feature construction for multivariate decoding


Brodersen, Kay H; Haiss, Florent; Ong, Cheng S; Jung, Fabienne; Tittgemeyer, Marc; Buhmann, Joachim M; Weber, Bruno; Stephan, Klaas E (2011). Model-based feature construction for multivariate decoding. NeuroImage, 56(2):601-615.

Abstract

Conventional decoding methods in neuroscience aim to predict discrete brain states from multivariate correlates of neural activity. This approach faces two important challenges. First, a small number of examples are typically represented by a much larger number of features, making it hard to select the few informative features that allow for accurate predictions. Second, accuracy estimates and information maps often remain descriptive and can be hard to interpret. In this paper, we propose a model-based decoding approach that addresses both challenges from a new angle. Our method involves (i) inverting a dynamic causal model of neurophysiological data in a trial-by-trial fashion; (ii) training and testing a discriminative classifier on a strongly reduced feature space derived from trial-wise estimates of the model parameters; and (iii) reconstructing the separating hyperplane. Since the approach is model-based, it provides a principled dimensionality reduction of the feature space; in addition, if the model is neurobiologically plausible, decoding results may offer a mechanistically meaningful interpretation. The proposed method can be used in conjunction with a variety of modelling approaches and brain data, and supports decoding of either trial or subject labels. Moreover, it can supplement evidence-based approaches for model-based decoding and enable structural model selection in cases where Bayesian model selection cannot be applied. Here, we illustrate its application using dynamic causal modelling (DCM) of electrophysiological recordings in rodents. We demonstrate that the approach achieves significant above-chance performance and, at the same time, allows for a neurobiological interpretation of the results.

Abstract

Conventional decoding methods in neuroscience aim to predict discrete brain states from multivariate correlates of neural activity. This approach faces two important challenges. First, a small number of examples are typically represented by a much larger number of features, making it hard to select the few informative features that allow for accurate predictions. Second, accuracy estimates and information maps often remain descriptive and can be hard to interpret. In this paper, we propose a model-based decoding approach that addresses both challenges from a new angle. Our method involves (i) inverting a dynamic causal model of neurophysiological data in a trial-by-trial fashion; (ii) training and testing a discriminative classifier on a strongly reduced feature space derived from trial-wise estimates of the model parameters; and (iii) reconstructing the separating hyperplane. Since the approach is model-based, it provides a principled dimensionality reduction of the feature space; in addition, if the model is neurobiologically plausible, decoding results may offer a mechanistically meaningful interpretation. The proposed method can be used in conjunction with a variety of modelling approaches and brain data, and supports decoding of either trial or subject labels. Moreover, it can supplement evidence-based approaches for model-based decoding and enable structural model selection in cases where Bayesian model selection cannot be applied. Here, we illustrate its application using dynamic causal modelling (DCM) of electrophysiological recordings in rodents. We demonstrate that the approach achieves significant above-chance performance and, at the same time, allows for a neurobiological interpretation of the results.

Statistics

Citations

16 citations in Web of Science®
15 citations in Scopus®
Google Scholar™

Altmetrics

Downloads

89 downloads since deposited on 18 May 2010
19 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:03 Faculty of Economics > Department of Economics
04 Faculty of Medicine > Institute of Pharmacology and Toxicology
07 Faculty of Science > Institute of Pharmacology and Toxicology

Special Collections > SystemsX.ch
Special Collections > SystemsX.ch > Research, Technology and Development Projects > Neurochoice
Dewey Decimal Classification:570 Life sciences; biology
610 Medicine & health
330 Economics
Language:English
Date:2011
Deposited On:18 May 2010 23:09
Last Modified:21 Nov 2017 14:51
Publisher:Elsevier
ISSN:1053-8119
Publisher DOI:https://doi.org/10.1016/j.neuroimage.2010.04.036
PubMed ID:20406688

Download

Download PDF  'Model-based feature construction for multivariate decoding'.
Preview
Content: Accepted Version
Filetype: PDF
Size: 2MB