AIXI, FEP-AI, and Integrated World Models: Towards a Unified Understanding of Intelligence and Consciousness

Abstract

Intelligence has been operationalized as both goal-pursuit capacity across a broad range of environments, and also as learning capacity above and beyond a foundational set of core priors. Within the normative framework of AIXI, intelligence may be understood as capacities for compressing (and thereby predicting) data and achieving goals via programs with minimal algorithmic complexity. Within the Free Energy Principle and Active Inference framework, intelligence may be understood as capacity for inference and learning of predictive models for goal-realization, with beliefs favored to the extent they fit novel data with minimal updating of priors. Most recently, consciousness has been proposed to enhance intelligent functioning by allowing for iterative state estimation of the essential variables of a system and its relationships to its environment, conditioned on a causal world model. This paper discusses machine learning architectures and principles by which all these views may be synergistically combined and contextualized with an Integrated World Modeling Theory of consciousness.

Making and breaking symmetries in mind and life

“…Symmetries and invariances are often first principles pointing to some lawful description of an observation, with explanations being understood as both 'satisfying' and potentially useful in their regularity [3][4][5]. The sense of aesthetic beauty accompanying such explanations is reminiscent of our understanding of intelligence in terms of the ability to efficiently predict (or compress) data [6,7]; indeed, identifying and building on symmetry can offer a particularly elegant description of a physical situation. The study of symmetries is so fundamental to mathematics and physics that one might ask where else it proves useful.…”