Metraipolis › archive › dc_dca968e9fbcf

High-rank connectivity scaffolds support precision and generalisation in recurrent neural networks — arXiv:2609.35207

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.35207
License (as archived): CC0-1.0
Archived: 2026-10-08T01:30:54.060Z
SHA-256 of the archived text: edfb7cda886f78fb38e98d53170a7d09e1515bf7d6d2aca0db0860c35a2a03e0
Stable URL of this page: https://metraipolis.com/documento/dc_dca968e9fbcf

How to cite

High-rank connectivity scaffolds support precision and generalisation in recurrent neural networks — arXiv:2609.35207 — arXiv (en), https://arxiv.org/abs/2609.35207 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dca968e9fbcf (Metraipolis archive dc_dca968e9fbcf, sha256 edfb7cda886f78fb38e98d53170a7d09e1515bf7d6d2aca0db0860c35a2a03e0)

BibTeX

@misc{dcdca968e9fbcf,
  title = {High-rank connectivity scaffolds support precision and generalisation in recurrent neural networks — arXiv:2609.35207},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35207},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dca968e9fbcf; sha256 edfb7cda886f78fb38e98d53170a7d09e1515bf7d6d2aca0db0860c35a2a03e0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35207. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A major challenge in neuroscience and machine learning is to connect single-neuron influence, population dynamics, and circuit connectivity in a causal account of computation. Much previous work has shown that low-rank connectivity can generate low-dimensional dynamics in trained artificial neural networks, but this leaves unclear the functional relevance of the higher-rank structure of biological neural circuits and many artificial neuronal networks. Here we analyse recurrent neural networks trained to locate rewards by integrating continuously varying speed inputs in one- and two-dimensional spatial tasks. We find that dominant low-dimensional dynamics encode task locations, and can be causally manipulated to instruct behavioural outcomes. However, after decomposing the underlying circuitry we found that while low-rank connectivity accounts for the low-dimensional dynamics, accurate performance and generalisation to novel speed distributions requires high-rank connectivity. We demonstrate that this is achieved through distributed signalling that corrects errors in low-dimensional location representations. Thus, combined perturbation-, representation-, and circuit-level analyses demonstrate a novel mechanism for robust spatial computation and show how high-rank connectivity in neural circuits can provide a scaffold that supports precision and generalisation.

Tema degli esploratori: scienze della vita e salute (retro-catalogo arXiv: annunci del 2026-09-29 in q-bio.NC).
Categorie arXiv: Neurons and Cognition (q-bio.NC).
Pagina del lavoro: https://arxiv.org/abs/2609.35207 — 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 2026-10-08T01:05:21.274Z dalla pagina https://arxiv.org/catchup/q-bio.NC/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).