Multiclass Sparse Bayesian Regression for fMRI-Based Prediction
Figure 1
Graphical model of Multiclass Sparse Bayesian Regression (MCBR). We denote by the targets to be predicted and by the set of activation images. both the weights of the model depend on a discrete variable that assigns each feature to a class among . Both the noise and the weights have a Gamma prior on their precisions. The variable follows a Dirichlet prior .