Item

Abstract

Pattern recognition methods have shown that fMRI data can reveal signicant information about brain activity. For example, in the debate of how object categories are represented
in the brain, multivariate analysis has been used to provide evidence of a distributed
encoding scheme. Many follow up studies have employed dierent methods to analyze
human fMRI data with varying degrees of success. In this presentation I would like
to discuss and compare four popular pattern recognition methods: correlation analysis,
support vector machines (SVM), linear discriminant analysis and Gaussian nave Bayes
(GNB), using data collected at high eld (7T) with higher resolution than usual fMRI
studies. We investigate prediction performance on single trials and for averages across
varying numbers of stimulus presentations. The performance of the various algorithms
depends on the nature of the brain activity being categorized: for several tasks, many of
the methods work well, whereas for others, no methods perform above chance level. An
important factor in overall classication performance is careful preprocessing of the data,
including dimensionality reduction, voxel selection, and outlier elimination.