Nonnegative Matrix Factorization with Gaussian Process Priors

<table>Brain imaging
data matrix (top) along with the estimated decomposition and residual for the
CNMF (middle) and GPP-NMF (bottom) methods. In this view, the results of the two
decompositions are very similar, the data appears to be modeled equally well
and the residuals are similar in magnitude.</table>

Computational Intelligence and Neuroscience

fig4

Figure 4

Figure 4: Nonnegative Matrix Factorization with Gaussian Process Priors 