Abstract
Brain decoding with multivariate classification and regression has provided a powerful framework for characterizing information encoded in population neural activity. Classification and regression models are respectively used to predict discrete and continuous variables of interest. However, cognitive and behavioral parameters that we wish to decode are often ordinal variables whose values are discrete but ordered, such as subjective ratings. To date, there is no established method of predicting ordinal variables in brain decoding. In this study, we present a new algorithm, sparse ordinal logistic regression (SOLR), that combines ordinal logistic regression with Bayesian sparse weight estimation. We found that, in both simulation and analyses using real functional magnetic resonance imaging (fMRI) data, SOLR outperformed ordinal logistic regression with non-sparse regularization, indicating that sparseness leads to better decoding performance. SOLR also outperformed classification and linear regression models with the same type of sparseness, indicating the advantage of the modeling tailored to ordinal outputs. Our results suggest that SOLR provides a principled and effective method of decoding ordinal variables.
Highlights
Application of multivariate classification and regression models to functional magnetic resonance imaging signals has allowed the extraction of information encoded in population neural activity
We demonstrate that sparse ordinal logistic regression (SOLR) better predicts ordinal variables in a practical situation of functional magnetic resonance imaging (fMRI) decoding analysis
We developed a new algorithm for ordinal variable decoding by combining ordinal logistic regression (OLR) with Bayesian sparse weight estimation
Summary
Application of multivariate classification and regression models to functional magnetic resonance imaging (fMRI) signals has allowed the extraction of information encoded in population neural activity. Discretized parameters could be better treated as ordinal variables Such variables have been predicted with classification and regression models in previous decoding studies. This treats the class number as a discrete variable without using the metric in the space of the output variable By tuning both linear weights and thresholds, ordinal regression models can be better fitted to given ordinal data than linear regression models. Stimulus images were reconstructed from fMRI responses by training decoders on 440 samples using about 1,000 voxels from the primary visual cortex (V1) in both hemispheres as input Using this dataset, we demonstrate that SOLR better predicts ordinal variables in a practical situation of fMRI decoding analysis
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
