Metraipolis › archive › dc_09cf48327ff5
Functional compatibility as a determinant of persistent neural learning — arXiv:2608.22462
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.22462
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T07:44:55.393Z
- SHA-256 of the archived text
0bb929b13a96926c6dea989748373cf23ff0cf8487a405252bd4b69bac488346- Stable URL of this page
https://metraipolis.com/documento/dc_09cf48327ff5
How to cite
Functional compatibility as a determinant of persistent neural learning — arXiv:2608.22462 — arXiv (en), https://arxiv.org/abs/2608.22462 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_09cf48327ff5 (Metraipolis archive dc_09cf48327ff5, sha256 0bb929b13a96926c6dea989748373cf23ff0cf8487a405252bd4b69bac488346)
BibTeX
@misc{dc09cf48327ff5,
title = {Functional compatibility as a determinant of persistent neural learning — arXiv:2608.22462},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.22462},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_09cf48327ff5; sha256 0bb929b13a96926c6dea989748373cf23ff0cf8487a405252bd4b69bac488346},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.22462. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Neural networks can acquire new capabilities while damaging existing ones, but what determines whether new learning persists remains unclear. We identify functional compatibility, the extent to which incoming learning can coexist with behaviour that must be preserved, as an experimentally manipulable causal determinant of persistence. From identical neural states, we vary compatibility while matching unrestricted learning opportunity and imposing a common retention requirement. Persistent learning increases with compatibility across independent directions, convolutional and transformer architectures, vision and text, and a ten-seed replication. Learning rules and retention constraints determine how much compatible opportunity is retained, whereas nonlinear geometry limits the matched intervention at larger update norms. Functional compatibility therefore reframes stability-plasticity from preventing forgetting to determining which new learning can coexist with existing function and persist. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-25 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.22462 — 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 2026-10-18T07:37:52.881Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).