Metraipolis › archive › dc_02e1c4dc15ca
Formation of structural attractors in neuromorphic systems — arXiv:2609.06826
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.06826
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T13:59:02.889Z
- SHA-256 of the archived text
674938405dfeea19f8bf3a2939aa08e98e6c5bea2635d08c98c6450607288926- Stable URL of this page
https://metraipolis.com/documento/dc_02e1c4dc15ca
How to cite
Formation of structural attractors in neuromorphic systems — arXiv:2609.06826 — arXiv (en), https://arxiv.org/abs/2609.06826 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_02e1c4dc15ca (Metraipolis archive dc_02e1c4dc15ca, sha256 674938405dfeea19f8bf3a2939aa08e98e6c5bea2635d08c98c6450607288926)
BibTeX
@misc{dc02e1c4dc15ca,
title = {Formation of structural attractors in neuromorphic systems — arXiv:2609.06826},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.06826},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_02e1c4dc15ca; sha256 674938405dfeea19f8bf3a2939aa08e98e6c5bea2635d08c98c6450607288926},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06826. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
This paper examines the theory of Invariant Structural Learning (ISL), which proposes a non-optimization approach to concept formation. Learning is interpreted as convergence to structural attractors in a hypergraph space, rather than as the minimization of a global loss function. The paper presents the ISL model, including its mathematical formalization, computational verification, and a hypothetical neurobiological interpretation. The mathematical section introduces the formal apparatus of the structural reduction process and proves its finite convergence, the existence and uniqueness of class structural attractors, and the self-organization of attractor maps. The computational section demonstrates the feasibility of the proposed approach on classical image recognition tasks, utilizing the proposed learning mechanism without backpropagation and with extremely small training datasets. Finally, the neurobiological section formulates hypotheses regarding the possible implementation of structural attractors in dendritic trees, neural coding as a projection of internal attractor dynamics, and the development of neural architectures supporting the proposed learning concept. These hypotheses are discussed in the context of modern experimental data in the fields of dendritic computations, synaptic plasticity, and the structural organization of neural circuits. The proposed neurobiological mechanisms are presented as testable hypotheses rather than established biological facts. The results demonstrate the mathematical consistency and computational feasibility of the proposed model, while the neurobiological hypotheses outline potential directions for its experimental verification. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.LG). Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE); Neurons and Cognition (q-bio.NC). Pagina del lavoro: https://arxiv.org/abs/2609.06826 — 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 2026-10-16T13:39:43.194Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).