Metraipolis › archive › dc_f271d5d004fe
Virtual neural networks: hundreds of souls in a body — arXiv:2609.24782
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.24782
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T22:06:22.318Z
- SHA-256 of the archived text
ad2d8be6d011d27d5691d0bb566d76185ad85d38e344503aa1dae0d295b38c1e- Stable URL of this page
https://metraipolis.com/documento/dc_f271d5d004fe
How to cite
Virtual neural networks: hundreds of souls in a body — arXiv:2609.24782 — arXiv (en), https://arxiv.org/abs/2609.24782 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f271d5d004fe (Metraipolis archive dc_f271d5d004fe, sha256 ad2d8be6d011d27d5691d0bb566d76185ad85d38e344503aa1dae0d295b38c1e)
BibTeX
@misc{dcf271d5d004fe,
title = {Virtual neural networks: hundreds of souls in a body — arXiv:2609.24782},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.24782},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f271d5d004fe; sha256 ad2d8be6d011d27d5691d0bb566d76185ad85d38e344503aa1dae0d295b38c1e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24782. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
A new concept, termed virtual neural networks, is introduced, where the count of trainable parameters is kept constant, and scalability is attained purely through computational resources. This concept is an abstract framework that can be realized using any standard convolutional neural network. It merges siamese neural networks with a deep ensemble technique by generating numerous virtual models that share weights derived from a small set of physical models. The ensemble comprises up to hundreds of trained models simultaneously. All virtual networks take the same input, and their interconnected structure induces an internal distortion that boosts the entire ensemble robustness. The accuracy of the ensemble improves as the number of virtual networks increases, without changing the capacity. Virtual neural networks outperform larger capacity models, typical deep ensembles, and contemporary approaches like SWA and Masksembles. Additionally, the highest-performing individual model from the ensemble surpasses other models trained individually, even those with a greater number of parameters. Code: this http URL Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.24782 — 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 2026-10-09T21:45:21.089Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).