Variational Bayesian Learning of Sparse Representations and Its Application in Functional Neuroimaging

Recent theoretical and experimental work in imaging neuroscience reveals that activations inferred from functional MRI data have sparse structure. We view sparse representation as a problem in Bayesian inference, following a machine learning approach, and construct a structured generative latent-variable model employing adaptive sparsity-inducing priors. The construction allows for automatic complexity control and regularization as well as denoising. Experimental results with benchmark datasets show that the proposed algorithm outperforms standard tools for model-free decompositions such as independent component analysis.