Free-Energy

We propose a formulation of expected free energy minimization based on a Bethe free energy functional, fully supporting inference by message passing. The epistemic drive is maintained by imposing an information constraint, in addition to normalisation, marginalisation and form constraints, insisting that the mutual information between future observations, states and parameters given actions must be at least as large as the entropy of the goal prior.

Artificial Intelligence should automate dangerous jobs instead of creative ones. I will present a framework for designing intelligent autonomous systems based on the Free Energy Principle, a leading physics-based theory of information processing in brains.

Natural AI is Artificial Intelligence based on physics principles. The Free Energy Principle allows for designing agents that learn in real-time, are low-power and are explainable. They are powered by Bayesian mechanics, updating beliefs over states of the world and actions as data streams in. At BIASlab and LazyDynamics, we have developed a toolbox for scalable automatic Bayesian inference called RxInfer.