Metraipolis › archive › dc_9939caf321a3

Neural Cellular Automata Learn General Features in their Hidden Channels — arXiv:2609.21870

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.21870
License (as archived)
CC0-1.0
Archived
2026-10-10T01:12:52.561Z
SHA-256 of the archived text
5891710a90a7e0518903f9c1756bf3fb986edcbc1dfc485c39a334e488f8960f
Stable URL of this page
https://metraipolis.com/documento/dc_9939caf321a3

How to cite

Neural Cellular Automata Learn General Features in their Hidden Channels — arXiv:2609.21870 — arXiv (en), https://arxiv.org/abs/2609.21870 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9939caf321a3 (Metraipolis archive dc_9939caf321a3, sha256 5891710a90a7e0518903f9c1756bf3fb986edcbc1dfc485c39a334e488f8960f)
BibTeX
@misc{dc9939caf321a3,
  title = {Neural Cellular Automata Learn General Features in their Hidden Channels — arXiv:2609.21870},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.21870},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9939caf321a3; sha256 5891710a90a7e0518903f9c1756bf3fb986edcbc1dfc485c39a334e488f8960f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.21870. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Modern deep learning models achieve impressive generalization through over-parameterization, but this paradigm often struggles with overfitting and memorization in few-shot regimes. Neural Cellular Automata (NCAs) offer a highly parameter-efficient alternative, yet research has focused primarily on their output, leaving the role of their internal hidden channels largely unexplored. In this paper, we investigate the internal dynamics of NCA hidden channels and introduce a novel transfer-learning mechanism that injects a pretrained teacher's hidden states into a student model to guide early optimization. Evaluated on few-shot and scale-variant MNIST benchmarks, NCAs outperform comparable recurrent and feed-forward architectures, demonstrating superior generalization with a minimal parameter budget (~9,800 parameters). Mechanistic analysis reveals that the hidden channels decouple feature extraction from uniform classification consensus by absorbing morphological complexity and converging to mutually orthogonal states. Furthermore, we demonstrate that these hidden channels capture general, scale-invariant topological primitives rather than class-specific templates. This allows a student model to achieve strong few-shot performance on unseen classes using features transferred from a teacher trained only on a subset of digits (0-5). Our results highlight the potential of utilizing hidden-state dynamics as a robust, decentralized computational substrate for parameter-efficient transfer learning

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-21 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.21870 — 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 2026-10-10T00:23:42.571Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).