Synthetic Data-Guided Symmetric Neural Network Approximation in Banach Spaces
Axioms · 20.08.2026 · 15 (8) · 623
DOI: 10.3390/axioms15080623 ↗Kurz gefasst
Fachartikel in der Zeitschrift Axioms, online erschienen am 20.08.2026. Verfasst von George A. Anastassiou und 2 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This paper develops a Banach space-valued approximation framework based on symmetrized neural network (SNN) operators generated by a deformation-dependent sigmoidal activation function. Symmetry is introduced directly at the activation level through a reciprocal-deformation mechanism, yielding a positive, even, normalized, and localized density kernel satisfying the partition of unity. The resulting construction provides normalized compact-interval and whole-line quasi-interpolation operators for Banach space-valued functions. Quantitative pointwise and uniform convergence estimates are established through the first modulus of continuity and are extended to higher-order and Caputo–Bochner fractional approximation. Numerical diagnostics support the theoretical kernel properties, and fractional approximation experiments compare the SNN and classical NN operators under common computational conditions. A controlled blind-prediction experiment on a synthetic monthly temperature-like series uses a strict fit–validation–test protocol and a parameter-matched operator comparison, with seasonal ARIMA and MLP models as external baselines. Across five independent realizations, the SNN attains the best mean predictive performance, with R2=0.9500, NMAE =0.0452, and NRMSE =0.0570. A vector-valued experiment in Y=R2 further illustrates the non-scalar applicability of the Banach space framework. In addition, the normalized SNN kernel weights provide an intrinsic node-level interpretation mechanism without requiring an external post hoc explainability method.
Zitieren
APA
Anastassiou, G. A., Karateke, S., & Zontul, M. (2026). Synthetic Data-Guided Symmetric Neural Network Approximation in Banach Spaces. Axioms, 15(8), 623. https://doi.org/10.3390/axioms15080623
Vancouver
Anastassiou GA, Karateke S, Zontul M. Synthetic Data-Guided Symmetric Neural Network Approximation in Banach Spaces. Axioms. 2026;15(8):623. doi:10.3390/axioms15080623
BibTeX
@article{Anastassiou2026,
author = {Anastassiou, George A. and Karateke, Seda and Zontul, Metin},
title = {Synthetic Data-Guided Symmetric Neural Network Approximation in Banach Spaces},
journal = {Axioms},
year = {2026},
volume = {15},
number = {8},
pages = {623},
doi = {10.3390/axioms15080623}
}
EUVIMED