Metraipolis › archive › dc_5e4e3880c69b
Non-Zero Radius: The Missing Component of Neural Networks — arXiv:2610.39559
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.39559
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T06:09:23.124Z
- SHA-256 of the archived text
c62cccb7490891897f0cab48f9973bc18d4745162dfc404e7a92cc66ecef3672- Stable URL of this page
https://metraipolis.com/documento/dc_5e4e3880c69b
How to cite
Non-Zero Radius: The Missing Component of Neural Networks — arXiv:2610.39559 — arXiv (en), https://arxiv.org/abs/2610.39559 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5e4e3880c69b (Metraipolis archive dc_5e4e3880c69b, sha256 c62cccb7490891897f0cab48f9973bc18d4745162dfc404e7a92cc66ecef3672)
BibTeX
@misc{dc5e4e3880c69b,
title = {Non-Zero Radius: The Missing Component of Neural Networks — arXiv:2610.39559},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.39559},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5e4e3880c69b; sha256 c62cccb7490891897f0cab48f9973bc18d4745162dfc404e7a92cc66ecef3672},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39559. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Inspired by the analogy between the all-or-none activation of biological neurons and the true-false of logic circuits, McCulloch and Pitts proposed a mathematical model of the biological neuron in 1943 with the aim of simulating logical reasoning. Although Norbert Wiener considered the model overly simplistic at the time, it later became a building block of modern neural networks, including large language models. Despite their remarkable empirical success, however, conventional neural networks remain largely black-box systems and struggle with reliable symbolic reasoning. Viewing vectors as spheres of zero radius, we relax the zero-radius constraint and represent concepts as spheres with non-zero radii. We argue that sphere-based representations can capture additional features of biological cognition, including representing spatial concepts as regions and reasoning through model construction and inspection. Building on sphere embeddings, we introduce Sphere Neural Networks (SphNNs), which use a transition map to achieve symbolic-level Aristotelian syllogistic reasoning without training data, thereby taking an initial step toward the original goal of McCulloch and Pitts. We suggest that the zero-radius constraint may reflect an aspect of the oversimplification identified by Wiener and may limit conventional neural networks' capacity for symbolic-level logical reasoning. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.39559 — 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 2026-10-31T06:07:08.531Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).