Relative Entropy, Probabilistic Inference, and AI

is an information-theoretic measure of the dissimilarity between q = q 1, • • · ,qn and p = p 11 • • • , pn (H is also called cross-entropy, discrimination information, directed divergence, !-divergence, K-L number, among other terms). Various properties of relative entropy have led to its widespread use in information theory. These properties suggest that relative entropy has a role to play in systems that attempt to perform inference in terms of probability distributions. In this paper, I will review some basic properties of relative entropy as well as its role in probabilistic inference. I will also mention briefly a few existing and potential applications of relative entropy to so-called artificial intelligence (AI).