juanshishido
commented
8 years ago [I]nstead of focusing on individual voxels, researchers use powerful pattern-classification algorithms, applied to multi-voxel patterns of activity, to decode the information that is represented in that pattern of activity. ... A major development in the last few years is the realization that fMRI data analysis can be construed, at a high level, as a pattern-classification problem (i.e. how we can recognize a pattern of brain activity as being associated with one cognitive state versus another). As such, all of the techniques that have been developed for pattern classification and data mining in other domains (e.g. handwriting recognition) can be productively applied to fMRI data analysis ... The ability to correlate classifier estimates with behavioral measures across trials (within individual subjects, over the course of a single experiment) is one of the most important benefits of the MVPA approach. ... The basic MVPA method is a straightforward application of pattern classification techniques, where the patterns to be classified are (typically) vectors of voxel activity values [emphasis added]. ... Most MVPA studies have used linear classifiers, including correlation-based classifiers, neural networks without a hidden layer, linear discriminant analysis, linear support vector machines (SVMs), and Gaussian Naive Bayes classifiers [emphasis added]. These classifiers all compute a weighted sum of voxel activity values; this weighted sum is then passed through a decision function, which effectively creates a threshold for saying whether or not a category is present.
—Norman, Polyn, Detre, and Haxby (2006)
Resources: