Self-orthogonalizing attractor neural networks emerging from the free energy principle

TL;DR

This paper presents a theoretical framework showing how self-organizing attractor neural networks can emerge from the free energy principle, leading to biologically plausible inference and learning dynamics with improved generalization.

Contribution

It formalizes the emergence of attractor networks from first principles, eliminating the need for explicit learning rules, and introduces a collective Bayesian active inference process.

Findings

Attractors encode prior beliefs and span input subspaces efficiently.

Networks favor approximately orthogonalized attractor representations.

Sequential data induces asymmetric couplings and non-equilibrium dynamics.

Abstract

Attractor dynamics are a hallmark of many complex systems, including the brain. Understanding how such self-organizing dynamics emerge from first principles is crucial for advancing our understanding of neuronal computations and the design of artificial intelligence systems. Here we formalize how attractor networks emerge from the free energy principle applied to a universal partitioning of random dynamical systems. Our approach obviates the need for explicitly imposed learning and inference rules and identifies emergent, but efficient and biologically plausible inference and learning dynamics for such self-organizing systems. These result in a collective, multi-level Bayesian active inference process. Attractors on the free energy landscape encode prior beliefs; inference integrates sensory data into posterior beliefs; and learning fine-tunes couplings to minimize long-term surprise. Analytically and via simulations, we establish that the proposed networks favor approximately orthogonalized attractor representations, a consequence of simultaneously optimizing predictive accuracy and model complexity. These attractors efficiently span the input subspace, enhancing generalization and the mutual information between hidden causes and observable effects. Furthermore, while random data presentation leads to symmetric and sparse couplings, sequential data fosters asymmetric couplings and non-equilibrium steady-state dynamics, offering a natural generalization of conventional Boltzmann Machines. Our findings offer a unifying theory of self-organizing attractor networks, providing novel insights for AI and neuroscience.