Abstract

A neural cellular automata (NCA) architecture, referred to as Pluto’s NCA, was developed to characterize bilateral communication and semantic reciprocity between symbolic representations and a spatially distributed update field. The architecture employs an encoder–automata–decoder pipeline that maps symbolic inputs into a multichannel state field and reconstructs them through agreement-driven attractor convergence within a stable semantic attractor landscape. System behavior was evaluated under controlled perturbations, including rhythmic desynchronization, graded ablations, correlated and independent noise, and percolation-based structural degradation. Quantities such as Agreement(t), internal coherence Aᵢ(t), the recovery time constant τ, and the critical percolation threshold pc were measured to assess stability, semantic homeostasis, and invariance under perturbation. Across the A0–A6 ablation series, Pluto’s NCA exhibited persistent attractor identity and functional invariance despite extensive structural loss. A phenomenon termed the Deadpool Effect was observed, defined as the preservation and full reconstruction of semantic identity when minimal contiguous state remained above a recoverable threshold. Recovery profiles consistently showed that internal coherence re-stabilized before external agreement, indicating a reciprocal alignment mechanism between symbolic encodings and neural-field dynamics. These results characterize Pluto’s NCA as a semantically invariant computational homeostat exhibiting stable attractor dynamics and recoverability across a wide range of perturbation magnitudes.

Recommended Citation

Assenza, Nicole (2025) "The Digital Neuron: Neural Cellular Automata for Neural–Symbolic Translation," SMU Data Science Review: Vol. 9: No. 3, Article 14.
Available at: https://scholar.smu.edu/datasciencereview/vol9/iss3/14