Metraipolis › archive › dc_723a2e4ee55b
Gaussian Neural Networks — arXiv:2609.34825
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.34825
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T21:02:58.927Z
- SHA-256 of the archived text
fdb3071cb99742472376cec6a851cadd8dda789a741cf07172a534284f9d379a- Stable URL of this page
https://metraipolis.com/documento/dc_723a2e4ee55b
How to cite
Gaussian Neural Networks — arXiv:2609.34825 — arXiv (en), https://arxiv.org/abs/2609.34825 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_723a2e4ee55b (Metraipolis archive dc_723a2e4ee55b, sha256 fdb3071cb99742472376cec6a851cadd8dda789a741cf07172a534284f9d379a)
BibTeX
@misc{dc723a2e4ee55b,
title = {Gaussian Neural Networks — arXiv:2609.34825},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.34825},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_723a2e4ee55b; sha256 fdb3071cb99742472376cec6a851cadd8dda789a741cf07172a534284f9d379a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34825. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Gaussian neural networks (GaNNs) are proposed as a novel regularization mechanism for neural networks. From a Bayesian perspective standard regularization techniques can be viewed as imposing priors over weight-space. Assuming priors over activation-space remains a largely unexplored possibility. GaNNs assume such priors. They do this by treating activities from earlier layers like signals with Gaussian noise and predicting the properties of the noise distribution using an additional unsupervised loss. While training, the unsupervised loss acts as a penalty on unexpected activities, allowing greater weight updates in less surprising directions. The paper demonstrates the superiority of Gaussian neural networks over standard neural networks on a variety of classification and regression tasks. We also investigate the ability of GaNNs to quantify uncertainty. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.34825 — 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 2026-10-07T20:29:03.167Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).