Metraipolis › archive › dc_a6ea2a46a119

Where Does Randomness Matter in Neural Cellular Automata? — arXiv:2609.36797

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.36797
License (as archived)
CC0-1.0
Archived
2026-10-07T17:29:29.693Z
SHA-256 of the archived text
4ddc0c0b6d544043595fcc046f0bc8f028742b4497aad819e767f33a76fba7bb
Stable URL of this page
https://metraipolis.com/documento/dc_a6ea2a46a119

How to cite

Where Does Randomness Matter in Neural Cellular Automata? — arXiv:2609.36797 — arXiv (en), https://arxiv.org/abs/2609.36797 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a6ea2a46a119 (Metraipolis archive dc_a6ea2a46a119, sha256 4ddc0c0b6d544043595fcc046f0bc8f028742b4497aad819e767f33a76fba7bb)
BibTeX
@misc{dca6ea2a46a119,
  title = {Where Does Randomness Matter in Neural Cellular Automata? — arXiv:2609.36797},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.36797},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a6ea2a46a119; sha256 4ddc0c0b6d544043595fcc046f0bc8f028742b4497aad819e767f33a76fba7bb},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36797. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Stochastic cell updates are often used throughout the life of a neural cellular automaton (NCA), from backpropagation through time to final rollout. This leaves two questions entangled: does update randomness help learn a useful rule, and must that randomness remain at execution? We separate training and evaluation update modes in controlled Growing NCA experiments, then vary the states shown during training. Under the standard constant-rate persist recipe, asynchronous training passes the short-horizon quality test in 10/10 runs, compared with 3/10 synchronous runs. All ten asynchronous models also retain the target for 4,096 steps under deterministic evaluation. For a scalar translation-invariant lattice, we derive an exact mean-square criterion: random masking can damp mean modes, but it also injects variance, and a mean-only test misclassifies four non-marginal settings. Finally, among 30 models that all pass the same reconstruction test, eight of ten grow-trained models become off-target at 4,096 steps, while all persist and regenerate models retain the target; damage recovery separates persist from regenerate. The results distinguish optimization reliability, execution mode, and task-specific behavior instead of treating them as one stability property.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Neural and Evolutionary Computing (cs.NE).
Pagina del lavoro: https://arxiv.org/abs/2609.36797 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T16:59:48.240Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).