Metraipolis › archive › dc_1d686ade3cb3
Phases in a class of associative memories via hidden neurons — arXiv:2609.10976
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.10976
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T05:54:52.052Z
- SHA-256 of the archived text
8c473e948da2dc7c578a9f47501d6cd1b826c37e9901228b0a5aeb4f34ccdee1- Stable URL of this page
https://metraipolis.com/documento/dc_1d686ade3cb3
How to cite
Phases in a class of associative memories via hidden neurons — arXiv:2609.10976 — arXiv (en), https://arxiv.org/abs/2609.10976 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1d686ade3cb3 (Metraipolis archive dc_1d686ade3cb3, sha256 8c473e948da2dc7c578a9f47501d6cd1b826c37e9901228b0a5aeb4f34ccdee1)
BibTeX
@misc{dc1d686ade3cb3,
title = {Phases in a class of associative memories via hidden neurons — arXiv:2609.10976},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.10976},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1d686ade3cb3; sha256 8c473e948da2dc7c578a9f47501d6cd1b826c37e9901228b0a5aeb4f34ccdee1},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.10976. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Associative memory in the Hopfield network is attractor dynamics in a disordered many-body system, and higher-order and exponential extensions turn its retrieval update into softmax attention. The polynomial and exponential regimes have been analyzed by different methods, with no common architecture in which to ask what fixes the storage scale. In this paper we study the bipartite architecture of Krotov and Hopfield, which we call the class $H$, whose model is fixed by a Lagrangian for each layer, taking the hidden neurons as the order parameter of retrieval. At polynomial load the replica method yields the replica-symmetric phase diagrams and closed-form capacities, and the crosstalk moment is common to Ising and spherical visible neurons, so their differences come from the visible entropy. With a softmax hidden layer the load is exponential, and a copy representation maps the thermodynamics onto random-energy-model counting, with paramagnetic, condensed, and frozen phases. Heating destabilizes retrieval by quantized reassignments of attention, and typical Gaussian patterns remain metastable at every load. The regimes differ in their crosstalk statistics, central-limit at polynomial load and large-deviation at exponential load, and the class $H$ splits retrieval into two roles, the visible Lagrangian fixing stability and the hidden one the storage scale, two axes that may also guide the design of new Lagrangians. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-11 in cs.LG). Categorie arXiv: Machine Learning (cs.LG) ; Disordered Systems and Neural Networks (cond-mat.dis-nn); Neural and Evolutionary Computing (cs.NE); Machine Learning (stat.ML). Pagina del lavoro: https://arxiv.org/abs/2609.10976 — 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 2026-10-16T05:44:24.965Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).