Metraipolis › archive › dc_fce9e67064fc

Safe-by-Design Learning via Energy-based Neural Networks — arXiv:2609.36942

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.36942
License (as archived)
CC0-1.0
Archived
2026-10-07T16:26:33.187Z
SHA-256 of the archived text
ff037bdcd803dc88e11e41568a49519c721261d13e4eb5cf304223102ad95451
Stable URL of this page
https://metraipolis.com/documento/dc_fce9e67064fc

How to cite

Safe-by-Design Learning via Energy-based Neural Networks — arXiv:2609.36942 — arXiv (en), https://arxiv.org/abs/2609.36942 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fce9e67064fc (Metraipolis archive dc_fce9e67064fc, sha256 ff037bdcd803dc88e11e41568a49519c721261d13e4eb5cf304223102ad95451)
BibTeX
@misc{dcfce9e67064fc,
  title = {Safe-by-Design Learning via Energy-based Neural Networks — arXiv:2609.36942},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.36942},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fce9e67064fc; sha256 ff037bdcd803dc88e11e41568a49519c721261d13e4eb5cf304223102ad95451},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36942. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Learning neural-network models of dynamical systems with safety guarantees is a fundamental requirement for their deployment in safety-critical settings. Safety is commonly established by proving the invariance of a desired subset in state-space, ensuring that every trajectory initialized in this subset remains confined to it for all time under admissible inputs. Existing frameworks, however, either rely on computationally expensive post-hoc verification or employ safety-enforcing mechanisms without formal correctness guarantees. In this paper, we introduce a novel neural architecture grounded in energy-based modern Hopfield networks to guarantee safety-by-design while retaining sufficient expressiveness to model complex nonlinear dynamics. Specifically, we integrate modern Hopfield networks with a port-Hamiltonian neural ODE, enabling by design the construction of barrier functions yielding explicit admissible-input sets and quantitative robustness radii. Across several benchmarks, including an 12-dimensional nanodrone model, our framework achieves state-of-the-art performance while producing certified invariant sets that are more robust to external solicitations than comparable existing approaches.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Systems and Control (eess.SY).
Pagina del lavoro: https://arxiv.org/abs/2609.36942 — 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 2026-10-07T15:54:53.909Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).