Deep active inference

Deep Active Inference

This work combines the free energy principle from cognitive neuroscience and the ensuing active inference dynamics with recent advances in variational inference in deep generative models, and evolution strategies as efficient large scale, black box optimisation technique, to introduce the “deep active inference” agent. This agent minimises a variational free energy bound on the average surprise...

Deep temporal models and active inference

How do we navigate a deeply structured world? Why are you reading this sentence first - and did you actually look at the fifth word? This review offers some answers by appealing to active inference based on deep temporal models. It builds on previous formulations of active inference to simulate behavioural and electrophysiological responses under hierarchical generative models of state transiti...

A Factor Graph Description of Deep Temporal Active Inference

Active inference is a corollary of the Free Energy Principle that prescribes how self-organizing biological agents interact with their environment. The study of active inference processes relies on the definition of a generative probabilistic model and a description of how a free energy functional is minimized by neuronal message passing under that model. This paper presents a tutorial introduc...

Deep Inference

Learning Deep Inference Machines

Introduction. The traditional approach to structured prediction problems is to craft a graphical model structure, learn parameters for the model, and perform inference using an efficient– and usually approximate– inference approach, including, e.g., graph cut methods, belief propagation, and variational methods. Unfortunately, while remarkably powerful methods for inference have been developed ...