Metraipolis › archive › dc_a6dad86d4fed
Basin Geometry and Reliable Recall of Dynamical Memories in Reservoir Computing — arXiv:2609.01914
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.01914
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T05:01:09.112Z
- SHA-256 of the archived text
004febe00a8e7f88d26c8380eaf1dc5e059d8b0b9784737fe5873d9d8bb87864- Stable URL of this page
https://metraipolis.com/documento/dc_a6dad86d4fed
How to cite
Basin Geometry and Reliable Recall of Dynamical Memories in Reservoir Computing — arXiv:2609.01914 — arXiv (en), https://arxiv.org/abs/2609.01914 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a6dad86d4fed (Metraipolis archive dc_a6dad86d4fed, sha256 004febe00a8e7f88d26c8380eaf1dc5e059d8b0b9784737fe5873d9d8bb87864)
BibTeX
@misc{dca6dad86d4fed,
title = {Basin Geometry and Reliable Recall of Dynamical Memories in Reservoir Computing — arXiv:2609.01914},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.01914},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a6dad86d4fed; sha256 004febe00a8e7f88d26c8380eaf1dc5e059d8b0b9784737fe5873d9d8bb87864},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01914. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Reliable attractor recall conventionally requires broad basins of attraction. However, in reservoir-computing based associative memory, temporal cues reliably recover dynamical memories despite basins dominated by unpredictable, riddled-like regions. We reveal that memory basins exhibit an ``octopus-like'' structure: a robust ``head'' near the attractor and thin, intertwined ``tentacles'' spanning state space. Initial states in tentacular regions yield near-zero uncertainty exponents, making the recalled memory effectively unpredictable at finite precision. Yet, cue-driven generalized synchronization bypasses this unpredictability, driving the system into the robust basin head. This mechanism yields a quantitative relation linking minimum cue duration, synchronization rate, and basin-head radius. Trained recurrent neural networks exhibit similar geometry, suggesting this phenomenon extends beyond reservoir computing. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-03 in cs.LG). Categorie arXiv: Chaotic Dynamics (nlin.CD) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.01914 — 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 2026-10-17T04:09:43.356Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).