EUVIMEDEUVIMED entdecken
Crossref

Constructing a class of neural network operators approximating integrable functions

Dansheng Yu, Renyi Xue, Feilong Cao

Analysis and Applications · 19.08.2026 · 1-40

DOI: 10.1142/s0219530526500697 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Analysis and Applications, online erschienen am 19.08.2026. Verfasst von Dansheng Yu und 2 weiteren Autor:innen. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Directly constructing feed forward neural networks (FNNs) as approximators and establishing their approximation theorems is extremely important. This paper employs a constructive technique to develop a broad and novel class of FNNs, proving the direct, inverse, and approximation characteristic equivalence theorems for Lebesgue integrable functions. This study’s primary innovations are: The proposed technique applies to a wide range of sigmoidal functions that form the activation function of the FNNs, including not just the conventional logistic and tangent functions. The established direct theorem of approximation reveals that the constructed FNN avoids the demand for training cycles and subsequent generalization testing, as well as avoiding local minimum in optimization; the obtained equivalence characterization theorem of approximation should be useful for designing FNN structures based on their approximation capacity. These theorems are built using [Formula: see text]-functionals, smoothness moduli, and the Berens–Lorentz lemma, as well as Jackson–Bernstein-type inequalities. Some numerical examples support the efficiency of the theoretical results.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Yu, D., Xue, R., & Cao, F. (2026). Constructing a class of neural network operators approximating integrable functions. Analysis and Applications, 1-40. https://doi.org/10.1142/s0219530526500697

Vancouver

Yu D, Xue R, Cao F. Constructing a class of neural network operators approximating integrable functions. Analysis and Applications. 2026:1-40. doi:10.1142/s0219530526500697

BibTeX
@article{Yu2026,
  author = {Yu, Dansheng and Xue, Renyi and Cao, Feilong},
  title = {Constructing a class of neural network operators approximating integrable functions},
  journal = {Analysis and Applications},
  year = {2026},
  pages = {1--40},
  doi = {10.1142/s0219530526500697}
}
Kostenlos starten →