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.
| Comments: | 27 pages main text, 8 pages appendix, 7 figures; interactive manuscript available at: this https URL Associated GitHub repository: this https URL |
| Subjects: | Neurons and Cognition (q-bio.NC); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE) |
| Cite as: | arXiv:2505.22749 [q-bio.NC] |
| (or arXiv:2505.22749v2 [q-bio.NC] for this version) | |
| https://doi.org/10.48550/arXiv.2505.22749 arXiv-issued DOI via DataCite |
|
| Journal reference: | Neurocomputing (2026): 133472 |
| Related DOI: | https://doi.org/10.1016/j.neucom.2026.133472
DOI(s) linking to related resources |
From: Tamas Spisak [view email]
[v1]
Wed, 28 May 2025 18:10:03 UTC (4,218 KB)
[v2]
Thu, 21 May 2026 10:17:37 UTC (5,315 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。