Metraipolis › archive › dc_20be9ca8ec2e
The Gaussian-Multinoulli Restricted Boltzmann Machine: A Potts Model Extension of the GRBM — arXiv:2505.11635
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2505.11635
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T06:08:43.948Z
- SHA-256 of the archived text
9355dd12d337e7c54b74a64474a0e86579d33307141f5153344d41cb2e3afa08- Stable URL of this page
https://metraipolis.com/documento/dc_20be9ca8ec2e
How to cite
The Gaussian-Multinoulli Restricted Boltzmann Machine: A Potts Model Extension of the GRBM — arXiv:2505.11635 — arXiv (en), https://arxiv.org/abs/2505.11635 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_20be9ca8ec2e (Metraipolis archive dc_20be9ca8ec2e, sha256 9355dd12d337e7c54b74a64474a0e86579d33307141f5153344d41cb2e3afa08)
BibTeX
@misc{dc20be9ca8ec2e,
title = {The Gaussian-Multinoulli Restricted Boltzmann Machine: A Potts Model Extension of the GRBM — arXiv:2505.11635},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2505.11635},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_20be9ca8ec2e; sha256 9355dd12d337e7c54b74a64474a0e86579d33307141f5153344d41cb2e3afa08},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2505.11635. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Many real-world tasks, from associative memory to symbolic reasoning, benefit from discrete, structured representations that standard continuous latent models can struggle to express. We introduce the Gaussian-Multinoulli Restricted Boltzmann Machine (GM-RBM), a generative energy-based model that extends the Gaussian-Bernoulli RBM (GB-RBM) by replacing binary hidden units with q-state categorical (Potts) units, yielding a richer latent state space for multivalued concepts. We provide a self-contained derivation of the energy, conditional distributions, and learning rules, and detail practical training choices (contrastive divergence with temperature annealing and intra-slot diversity constraints) that avoid state collapse. To separate architectural effects from sheer latent capacity, we evaluate under both capacity-matched and parameter-matched setups, comparing GM-RBM with GB-RBM configured to have the same number of possible latent assignments. On analogical recall and structured memory benchmarks, GM-RBM achieves competitive, and in several regimes improved, recall at equal capacity with comparable training cost, despite using only Gibbs updates. The discrete q-ary formulation is also amenable to efficient implementation. These results clarify when categorical hidden units provide a simple, scalable alternative to binary latents for discrete inference within tractable RBMs. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-12 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2505.11635 — 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 2026-10-19T05:57:28.314Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).