Random Projection Neural Networks of Best Approximation: Convergence Theory and Practical Applications
SIAM Journal on Mathematics of Data Science · 30.06.2025 · 7 (2) · 385-409
DOI: 10.1137/24m1639890 ↗Kurz gefasst
Fachartikel in der Zeitschrift SIAM Journal on Mathematics of Data Science, online erschienen am 07.04.2025. Verfasst von Gianluca Fabiani. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 75 Literaturangaben.
Abstract (Originalsprache)
We investigate the concept of best approximation for feedforward neural networks (FNNs) and explore their convergence properties through the lens of random projection neural networks (RPNNs). RPNNs have predetermined and permanently fixed internal weights and biases, offering computational efficiency. We demonstrate that there exists a choice of external weights, for any family of such RPNNs, with nonpolynomial infinitely differentiable activation functions, that exhibit an exponential convergence rate when approximating any infinitely differentiable function. For illustration purposes, we test the proposed RPNN-based function approximation, with parsimoniously chosen basis functions, across five benchmark function approximation problems. Results show that RPNNs achieve performance comparable to established methods, such as Legendre polynomials, highlighting their potential for efficient and accurate function approximation.
Zitieren
APA
Fabiani, G. (2025). Random Projection Neural Networks of Best Approximation: Convergence Theory and Practical Applications. SIAM Journal on Mathematics of Data Science, 7(2), 385-409. https://doi.org/10.1137/24m1639890
Vancouver
Fabiani G. Random Projection Neural Networks of Best Approximation: Convergence Theory and Practical Applications. SIAM Journal on Mathematics of Data Science. 2025;7(2):385-409. doi:10.1137/24m1639890
BibTeX
@article{Fabiani2025,
author = {Fabiani, Gianluca},
title = {Random Projection Neural Networks of Best Approximation: Convergence Theory and Practical Applications},
journal = {SIAM Journal on Mathematics of Data Science},
year = {2025},
volume = {7},
number = {2},
pages = {385--409},
doi = {10.1137/24m1639890}
}
EUVIMED