Structured Fluctuations and the Information Dynamics of Self-Maintenance in Growing Neural Cellular Automata

• URL: http://arxiv.org/abs/2607.12403v1
• Date: Tue, 14 Jul 2026 06:23:20 GMT
• Title: Structured Fluctuations and the Information Dynamics of Self-Maintenance in Growing Neural Cellular Automata
• Abstract summary: Growing Neural Cellular Automata (GNCA) are capable of robust self-maintenance and self-repair.<n>We show that internal fluctuations serve as a functional component supporting information flow, coordination, and return toward an attracting recurrent state.
• Score: 0.7498027847107155
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Growing Neural Cellular Automata (GNCA) are capable of robust self-maintenance and self-repair, yet the internal dynamical mechanisms that support these capabilities remain poorly understood. Here, we investigate the role of internal fluctuations--temporal micro-variability of hidden channel states--in a trained GNCA model, challenging the assumption that such variability is merely residual stochastic noise. Through systematic analysis spanning update-rate sweeps, spatial correlation measurements, dimensionality reduction of collective state trajectories, localized damage experiments, transfer entropy vector field estimation, and partial information decomposition, we show that internal fluctuations are spatially structured, dynamically coupled to an attracting collective state, and associated with distributed small-magnitude updates that contribute to damage recovery. Damage induces a global deviation in latent state space followed by gradual re-convergence, and suppressing distributed small-magnitude updates associated with baseline fluctuation dynamics outside a permissive radius that encompasses the majority of the cells significantly impairs recovery. Transfer entropy analysis characterizes a spatially differentiated repair response: corrective inward flow near the damage site coexists with outward perturbation propagation at greater distances. Partial information decomposition further suggests a regime shift from synergy-dominant resting computation to redundancy-increased coordination during recovery. These findings indicate that GNCA self-repair emerges from high-dimensional nonlinear collective dynamics in which internal fluctuations serve as a functional component supporting information flow, coordination, and return toward an attracting recurrent state.

Related papers

• Divisive Normalization Shapes Low-Rank Slow Manifolds for Continuous Working Memory [6.1311571881384745]
  We show that divisive normalization is mathematically essential to prevent manifold shattering under time-varying inputs.<n>Our findings identify divisive normalization as a critical computational mechanism for learning high-fidelity continuous representations.
  arXiv  Detail & Related papers  (2026-08-03T09:20:05Z)
• GLU: Global-Local-Uncertainty Fusion for Scalable Spatiotemporal Reconstruction and Forecasting [0.0]
  We present GLU, a Global-Local-Uncertainty framework that formulates sparse reconstruction and dynamic forecasting.<n>For reconstruction, GLU uses importance-aware adaptive neighborhood selection to retrieve locally relevant information.<n>For forecasting, a hierarchical Leader-Follower Dynamics module evolves the latent state with substantially reduced memory growth.
  arXiv  Detail & Related papers  (2026-03-27T02:40:58Z)
• Interaction-Enabled Hartree Fixed Points in Fermionic Resetting Dynamics [0.0]
  In resetting dynamics, a system is repeatedly coupled to and decoupled from ancillary degrees of freedom that are recoupled between interactions.<n>This provides a versatile route to engineer nonequilibrium states and constitutes a powerful and analytically transparent framework for studying nonequilibrium dynamics in fermionic models.<n>We introduce a Hartree mean-field treatment of density-density interactions that preserves closure of the SPDM dynamics while producing genuinely nonlinear behavior.
  arXiv  Detail & Related papers  (2026-03-16T17:14:08Z)
• On Exact Editing of Flow-Based Diffusion Models [97.0633397035926]
  We propose Conditioned Velocity Correction (CVC) to reformulate flow-based editing as a distribution transformation problem driven by a known source prior.<n>CVC rethinks the role of velocity in inter-distribution transformation by introducing a dual-perspective velocity conversion mechanism.<n>We show that CVC consistently achieves superior fidelity, better semantic alignment, and more reliable editing behavior across diverse tasks.
  arXiv  Detail & Related papers  (2025-12-30T06:29:20Z)
• Unleashing Temporal Capacity of Spiking Neural Networks through Spatiotemporal Separation [67.69345363409835]
  Spiking Neural Networks (SNNs) are considered naturally suited for temporal processing, with membrane potential propagation widely regarded as the core temporal modeling mechanism.<n>We design Non-Stateful (NS) models progressively removing membrane propagation to its stage-wise role. Experiments reveal a counterintuitive phenomenon: moderate removal in shallow layers improves performance, while excessive removal causes collapse.
  arXiv  Detail & Related papers  (2025-12-05T07:05:53Z)
• Drift No More? Context Equilibria in Multi-Turn LLM Interactions [58.69551510148673]
  contexts drift is the gradual divergence of a model's outputs from goal-consistent behavior across turns.<n>Unlike single-turn errors, drift unfolds temporally and is poorly captured by static evaluation metrics.<n>We show that multi-turn drift can be understood as a controllable equilibrium phenomenon rather than as inevitable decay.
  arXiv  Detail & Related papers  (2025-10-09T04:48:49Z)
• Noradrenergic-inspired gain modulation attenuates the stability gap in joint training [44.99833362998488]
  Studies in continual learning have identified a transient drop in performance on mastered tasks when assimilating new ones, known as the stability gap.<n>We argue that it reflects an imbalance between rapid adaptation and robust retention at task boundaries.<n>Inspired by locus coeruleus mediated noradrenergic bursts, we propose uncertainty-modulated gain dynamics.
  arXiv  Detail & Related papers  (2025-07-18T16:34:06Z)
• Quasiconservation Laws and Suppressed Transport in Weakly Interacting Localized Models [0.0]
  We investigate the perturbative stability of noninteracting localization under weak interactions.<n>We find that corrections to noninteracting local integrals of motion converge at large system sizes.<n>We find that the charge transport capacity remains bounded in the presence of interactions.
  arXiv  Detail & Related papers  (2025-07-03T18:53:17Z)
• Allostatic Control of Persistent States in Spiking Neural Networks for perception and computation [79.16635054977068]
  We introduce a novel model for updating perceptual beliefs about the environment by extending the concept of Allostasis to the control of internal representations.<n>In this paper, we focus on an application in numerical cognition, where a bump of activity in an attractor network is used as a spatial numerical representation.
  arXiv  Detail & Related papers  (2025-03-20T12:28:08Z)
• Neural State-Space Modeling with Latent Causal-Effect Disentanglement [3.5507435095193896]
  We discuss a novel technique for reconstructing local activity that, while small in signal strength, is the cause of subsequent global activities that have larger signal strength. Our central innovation is to approach this by explicitly modeling and disentangling how the latent state of a system is influenced by potential hidden internal interventions. Because the intervention can not be directly observed but have to be disentangled from the observed subsequent effect, we integrate knowledge of the native intervention-free dynamics of a system, and infer the hidden intervention by assuming it to be responsible for differences observed between the actual and hypothetical intervention-free dynamics.
  arXiv  Detail & Related papers  (2022-09-26T03:02:20Z)
• Input correlations impede suppression of chaos and learning in balanced rate networks [58.720142291102135]
  Information encoding and learning in neural circuits depend on how well time-varying stimuli can control spontaneous network activity. We show that in firing-rate networks in the balanced state, external control of recurrent dynamics, strongly depends on correlations in the input.
  arXiv  Detail & Related papers  (2022-01-24T19:20:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.