Metraipolis › archive › dc_00a0918c9599

Thermodynamic learning — arXiv:2609.04732

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.04732
License (as archived): CC0-1.0
Archived: 2026-10-17T00:05:39.006Z
SHA-256 of the archived text: d60dc3d21738e8f928c517514c9ee263e6afe7015665340b3319ea6dac242dbd
Stable URL of this page: https://metraipolis.com/documento/dc_00a0918c9599

How to cite

Thermodynamic learning — arXiv:2609.04732 — arXiv (en), https://arxiv.org/abs/2609.04732 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_00a0918c9599 (Metraipolis archive dc_00a0918c9599, sha256 d60dc3d21738e8f928c517514c9ee263e6afe7015665340b3319ea6dac242dbd)

BibTeX

@misc{dc00a0918c9599,
  title = {Thermodynamic learning — arXiv:2609.04732},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.04732},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_00a0918c9599; sha256 d60dc3d21738e8f928c517514c9ee263e6afe7015665340b3319ea6dac242dbd},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04732. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We discuss the possibility to train a thermodynamic system, whose micro-variables are fully determined through the Hamiltonian by the usual statistical mechanical rules, to perform tasks such as memorization and generalization. Training is achieved by the application of suitable external fields, playing the role of {\it data}. At variance with conventional machine learning, no other logical or algorithmic rules are introduced. The system is amenable, in principle, to exact analytical calculations. We specialize this general approach to a prototypical Ising system with annealed dichotomous couplings and study its learning ability. Results indicate excellent memorization and good generalization capacity already for small systems, and a tendency to improve with system size.

Tema degli esploratori: fisica e astronomia (retro-catalogo arXiv: annunci del 2026-09-07 in cond-mat.stat-mech).
Categorie arXiv: Statistical Mechanics (cond-mat.stat-mech) ; Disordered Systems and Neural Networks (cond-mat.dis-nn).
Pagina del lavoro: https://arxiv.org/abs/2609.04732 — 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 2026-10-16T23:41:28.027Z dalla pagina https://arxiv.org/catchup/cond-mat.stat-mech/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).