Double Contingency of Communications in Bayesian Learning

In previous work, we described the geometry of Bayesian learning on a manifold. this paper, inspired by notion modified double contingency communications from sociologist Niklas Luhmann, take two manifolds in equal parts and potential function their product to set up mutual learning. Particularly, given parametric statistical model, consider between copies parameter space. Here, associate with relative entropy (i.e., Kullback–Leibler divergence). Although forgets all elements about model except entropy, it still substitutes for usual estimation certain case. We propose as globalization information geometry.