In this study, we suggest an information-theoretic brain model, assuming that the fMRI recordings of a subject, who performs a cognitive task, are the observable signals, generated by the anatomical regions, each of which can be represented as an information source. Based upon this assumption, we define two versions of Shannon entropy, namely, dynamic and static entropy to analyze the information content of anatomical regions during a cognitive state. We also propose two network models by estimating dynamic and static Kullback-Leibler (K-L) divergences to investigate the interactions across the anatomical regions.