Reviews: Cross-Spectral Factor Analysis

The authors propose a factor analysis method called CSFA for modelling LFP data, which is a generative model with the specific assumption that factors, called Elecotomes, are sampled from Gaussian processes with cross-spectral mixture kernel. The generative model is straightforward use of CSM, and the estimation is apparently also a known form (resilient back prop; I never heard of it before). I do like the dCSFA formulation. The proposed method focuses on spectral power and phase relationship across regions, and is claimed to bring both better interpretability and higher predictive power. They also extend CSFA to be discriminative to side information such as genetic and behavioral data by incorporating logistic loss (or the likes of it).