Metraipolis › archive › dc_ceee1e68fa61

Storing Infinite Dynamical Attractors in Nonreciprocal Associative Neural Networks — arXiv:2609.07341

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.07341
License (as archived)
CC0-1.0
Archived
2026-10-16T16:01:04.942Z
SHA-256 of the archived text
147fa258fe72e3f2f1280530c9b39cdda4132e74b00009ddbc5958d5f9cc05f5
Stable URL of this page
https://metraipolis.com/documento/dc_ceee1e68fa61

How to cite

Storing Infinite Dynamical Attractors in Nonreciprocal Associative Neural Networks — arXiv:2609.07341 — arXiv (en), https://arxiv.org/abs/2609.07341 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ceee1e68fa61 (Metraipolis archive dc_ceee1e68fa61, sha256 147fa258fe72e3f2f1280530c9b39cdda4132e74b00009ddbc5958d5f9cc05f5)
BibTeX
@misc{dcceee1e68fa61,
  title = {Storing Infinite Dynamical Attractors in Nonreciprocal Associative Neural Networks — arXiv:2609.07341},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.07341},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ceee1e68fa61; sha256 147fa258fe72e3f2f1280530c9b39cdda4132e74b00009ddbc5958d5f9cc05f5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07341. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We develop a dynamical mean-field theory for nonreciprocal associative networks that store an extensive number of dynamical attractors, from limit cycles to strange attractors. Using a path integral calculation under quenched disorder, we derive self-consistent dynamical mean-field equations for pattern overlaps, autocorrelations and response functions. Memory retrieval capacity is governed by the spectral structure of the coupling matrices encoding stored patterns. When their eigenvalues are coherently aligned, retarded self-interactions and quenched noise feed back destructively: at zero eigenphase (fixed point attractors) the classical equilibrium capacity bound is recovered, while for limit cycles retrieval collapses far below it. In contrast, for uniformly distributed eigenphases, retarded self-interactions and much of the quenched noise cancels, reducing the dynamics to an effective single-spin process and amplifying capacity substantially. We validate the theory against microscopic simulations for limit-cycle and chaotic attractors, identifying eigenvalue decoherence as the mechanism enabling enhanced storage of dynamical memories.

Tema degli esploratori: fisica e astronomia (retro-catalogo arXiv: annunci del 2026-09-09 in cond-mat.stat-mech).
Categorie arXiv: Disordered Systems and Neural Networks (cond-mat.dis-nn) ; Statistical Mechanics (cond-mat.stat-mech).
Pagina del lavoro: https://arxiv.org/abs/2609.07341 — 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 2026-10-16T15:44:27.768Z dalla pagina https://arxiv.org/catchup/cond-mat.stat-mech/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).