Metraipolis › archive › dc_c93f2256ab48
Canonical locks that encode part-whole hierarchies — arXiv:2609.26046
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.26046
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T13:45:25.359Z
- SHA-256 of the archived text
f1079fa3c58ca5df412d79c44781749b80b1616f3e409f99293da4d28c1bc1dc- Stable URL of this page
https://metraipolis.com/documento/dc_c93f2256ab48
How to cite
Canonical locks that encode part-whole hierarchies — arXiv:2609.26046 — arXiv (en), https://arxiv.org/abs/2609.26046 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c93f2256ab48 (Metraipolis archive dc_c93f2256ab48, sha256 f1079fa3c58ca5df412d79c44781749b80b1616f3e409f99293da4d28c1bc1dc)
BibTeX
@misc{dcc93f2256ab48,
title = {Canonical locks that encode part-whole hierarchies — arXiv:2609.26046},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.26046},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c93f2256ab48; sha256 f1079fa3c58ca5df412d79c44781749b80b1616f3e409f99293da4d28c1bc1dc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.26046. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
One of the challenges in representational learning is how to encode part-whole hierarchies in a neural net. Prior works rely on flattening tree-like structures into string-like sequences and training a sequence-to-sequence model via autoregression. While such a representation works for parse-trees in NLP, it is not entirely clear how to make it work for images. Thus, we propose a geometric primitive called canonical locks. The key idea is that parts/wholes can be modelled as higher-dimensional vectors ($d \geq 4$), and information can be encoded in their relative phase differences. Inductively, the net consists of positionally-bound bottom-up and top-down neural fields, which drive each other to achieve a state of thermal equilibrium. Additionally, we show the existence of a few symmetrical configurations in the net. The computational iterations taken to break these symmetries depend on the angle between parts/wholes arranged on a disk (or more precisely a ring) in higher dimensions. It also appears to have connections to the psychological phenomenon of mental rotation. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.26046 — 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 2026-10-08T13:18:38.133Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).