EUVIMEDEUVIMED entdecken
Crossref

HyRNN: Hybrid Recurrent Neural Networks for Approximating Hybrid Dynamical Systems

Ricardo G. Sanfelice

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (30) · 25184-25191

DOI: 10.1609/aaai.v40i30.39709 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Ricardo G. Sanfelice.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

For a class of hybrid dynamical systems, we show that a recurrent neural network with hybrid dynamics, which we refer to as a hybrid dynamic recurrent neural network (HyRNN), can be constructed to approximate solutions to hybrid systems over bounded (hybrid) time horizons. Specifically, given a desired precision level, we show that a hybrid system with dynamics resembling those of recurrent neural networks for continuous-time and discrete-time systems can be designed so that, for each bounded hybrid time horizon, its solutions are close to the solutions to the given hybrid system. Through the use of universal approximation theorems, we show that the approximation result holds for traditional smooth activation functions, such as sigmoid and arctan, and that extensions to ReLU functions are possible, and characterize the complexity of the proposed HyRNN.

Zitieren

APA

Sanfelice, R. G. (2026). HyRNN: Hybrid Recurrent Neural Networks for Approximating Hybrid Dynamical Systems. Proceedings of the AAAI Conference on Artificial Intelligence, 40(30), 25184-25191. https://doi.org/10.1609/aaai.v40i30.39709

Vancouver

Sanfelice RG. HyRNN: Hybrid Recurrent Neural Networks for Approximating Hybrid Dynamical Systems. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(30):25184-25191. doi:10.1609/aaai.v40i30.39709

BibTeX
@article{Sanfelice2026,
  author = {Sanfelice, Ricardo G.},
  title = {HyRNN: Hybrid Recurrent Neural Networks for Approximating Hybrid Dynamical Systems},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {30},
  pages = {25184--25191},
  doi = {10.1609/aaai.v40i30.39709}
}
Kostenlos starten →