SpaceNet implements spatial penalties which improve brain decoding power as well as decoder maps:
These regularize classification and regression problems in brain imaging. The result are brain maps which are both sparse (i.e regression coefficients are zero everywhere, except at predictive voxels) and structured (blobby). The superiority of TV-L1 over methods without structured priors like the Lasso, SVM, ANOVA, Ridge, etc. for yielding more interpretable maps and improved prediction scores is now well established [Baldassarre et al. 2012], [Gramfort et al. 2013], [Grosenick et al. 2013].
Note that TV-L1 prior leads to a difficult optimization problem, and so can be slow to run. Under the hood, a few heuristics are used to make things a bit faster. These include:
The complete script can be found here.