Satake Emi, Majima Kei, Aoki Shuntaro C, Kamitani Yukiyasu
Graduate School of Informatics, Kyoto University, Kyoto, Japan.
ATR Computational Neuroscience Laboratories, Kyoto, Japan.
Front Neuroinform. 2018 Aug 15;12:51. doi: 10.3389/fninf.2018.00051. eCollection 2018.
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.
利用多元分类和回归进行脑解码为表征群体神经活动中编码的信息提供了一个强大的框架。分类和回归模型分别用于预测感兴趣的离散变量和连续变量。然而，我们希望解码的认知和行为参数通常是有序变量，其值是离散但有序的，例如主观评分。迄今为止，在脑解码中还没有既定的预测有序变量的方法。在本研究中，我们提出了一种新算法，即稀疏有序逻辑回归（SOLR），它将有序逻辑回归与贝叶斯稀疏权重估计相结合。我们发现，在使用真实功能磁共振成像（fMRI）数据的模拟和分析中，SOLR均优于具有非稀疏正则化的有序逻辑回归，这表明稀疏性可带来更好的解码性能。SOLR在具有相同稀疏类型的情况下也优于分类和线性回归模型，这表明针对有序输出进行建模具有优势。我们的结果表明，SOLR为解码有序变量提供了一种有原则且有效的方法。
