Integrated World Modeling Theory (IWMT) Expanded: Implications for Theories of Consciousness and Artificial Intelligence

Integrated World Modeling Theory (IWMT) combines the Free Energy Principle and Active Inference with Integrated Information Theory and Global Neuronal Workspace Theory to offer a unified account of consciousness. The theory emphasizes predictive processing models, autoencoders, turbo-codes, and graph neural networks, and highlights the hippocampal/entorhinal system's role in high-level reasoning and conscious access. It suggests novel methods for estimating integrated information using probabilistic graphical models, flow networks, and game theory, and addresses the "Bayesian blur problem"—how discrete experience arises from probabilistic modeling. The article also explores parallels with theories of universal intelligence and implications for artificial intelligence, particularly recurrent computation and symbol grounding.

Study at a glance

Abstract

Integrated World Modeling Theory (IWMT) is a synthetic theory of consciousness that uses the Free Energy Principle and Active Inference (FEP-AI) framework to combine insights from Integrated Information Theory (IIT) and Global Neuronal Workspace Theory (GNWT). Here, I first review philosophical principles and neural systems contributing to IWMT’s integrative perspective. I then go on to describe predictive processing models of brains and their connections to machine learning architectures, with particular emphasis on autoencoders (perceptual and active inference), turbo-codes (establishment of shared latent spaces for multi-modal integration and inferential synergy), and graph neural networks (spatial and somatic modeling and control). Particular emphasis is placed on the hippocampal/entorhinal system, which may provide a source of high-level reasoning via predictive contrasting and generalized navigation, so affording multiple kinds of conscious access. Future directions for IIT and GNWT are considered by exploring ways in which modules and workspaces may be evaluated as both complexes of integrated information and arenas for iterated Bayesian model selection. Based on these considerations, I suggest novel ways in which integrated information might be estimated using concepts from probabilistic graphical models, flow networks, and game theory. Mechanistic and computational principles are also considered with respect to the ongoing debate between IIT and GNWT regarding the physical substrates of different kinds of conscious and unconscious phenomena. I further explore how these ideas might relate to the “Bayesian blur problem”, or how it is that a seemingly discrete experience can be generated from probabilistic modeling, with some consideration of analogies from quantum mechanics as potentially revealing different varieties of inferential dynamics. Finally, I go on to describe parallels between FEP-AI and theories of universal intelligence, including with respect to implications for the future of artificially intelligent systems. Particular emphasis is given to recurrent computation and its relationships with feedforward processing, including potential means of addressing critiques of causal structure theories based on network unfolding, and the seeming absurdity of conscious expander graphs (without cybernetic symbol grounding). While not quite solving the Hard problem, this article expands on IWMT as a unifying model of consciousness and the potential future evolution of minds.