Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA 15213-3891, USA.
Neuroimage. 2011 May 15;56(2):716-27. doi: 10.1016/j.neuroimage.2010.04.271. Epub 2010 May 5.
Recent multivariate analyses of fMRI activation have shown that discriminative classifiers such as Support Vector Machines (SVM) are capable of decoding fMRI-sensed neural states associated with the visual presentation of categories of various objects. However, the lack of a generative model of neural activity limits the generality of these discriminative classifiers for understanding the underlying neural representation. In this study, we propose a generative classifier that models the hidden factors that underpin the neural representation of objects, using a multivariate multiple linear regression model. The results indicate that object features derived from an independent behavioral feature norming study can explain a significant portion of the systematic variance in the neural activity observed in an object-contemplation task. Furthermore, the resulting regression model is useful for classifying a previously unseen neural activation vector, indicating that the distributed pattern of neural activities encodes sufficient signal to discriminate differences among stimuli. More importantly, there appears to be a double dissociation between the two classifier approaches and within- versus between-participants generalization. Whereas an SVM-based discriminative classifier achieves the best classification accuracy in within-participants analysis, the generative classifier outperforms an SVM-based model which does not utilize such intermediate representations in between-participants analysis. This pattern of results suggests the SVM-based classifier may be picking up some idiosyncratic patterns that do not generalize well across participants and that good generalization across participants may require broad, large-scale patterns that are used in our set of intermediate semantic features. Finally, this intermediate representation allows us to extrapolate the model of the neural activity to previously unseen words, which cannot be done with a discriminative classifier.
最近对 fMRI 激活的多元分析表明，判别分类器（如支持向量机 (SVM)）能够解码与各种物体类别视觉呈现相关的 fMRI 感知神经状态。然而，缺乏神经活动的生成模型限制了这些判别分类器在理解潜在神经表示方面的通用性。在这项研究中，我们提出了一种生成分类器，使用多元多元线性回归模型对潜在的神经表示的隐藏因素进行建模。结果表明，从独立的行为特征标准化研究中得出的对象特征可以解释对象沉思任务中观察到的神经活动中系统方差的很大一部分。此外，所得回归模型可用于对以前看不见的神经激活向量进行分类，表明神经活动的分布式模式编码了足以区分刺激差异的信号。更重要的是，这两种分类器方法似乎存在双重分离，以及参与者内和参与者间的泛化。虽然基于 SVM 的判别分类器在参与者内分析中达到了最佳的分类准确性，但生成分类器在参与者间分析中优于不利用此类中间表示的基于 SVM 的模型。这种结果模式表明，基于 SVM 的分类器可能会捕获一些不能很好地在参与者之间推广的特殊模式，而在参与者之间进行良好的推广可能需要广泛的、大规模的模式，这些模式用于我们的一组中间语义特征中。最后，这种中间表示允许我们将神经活动模型外推到以前看不见的单词，这是判别分类器无法做到的。
