Efficient Approximation of Goldbach Partition Function Using Machine Learning Models
IEEE Access · 2026 · 14 · 83095-83108
DOI: 10.1109/access.2026.3690991 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Cheng-Zhe Wu und 1 weiteren Autor:innen. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Science and Technology Council, Taiwan.
Abstract (Originalsprache)
Goldbach’s conjecture, still unproven, posits that every even integer greater than 2 can be expressed as the sum of two primes. The Goldbach partition function $G(n)$ counts the number of such prime pairs for even integer $n \gt 2$ . While several analytic approximations exist, recent studies have explored machine learning approaches to estimate $G(n)$ . Building on prior architectures, we propose refined models that integrate Euler’s totient function $\varphi (n)$ as a primary feature, combined with nonlinear logarithmic-exponential transformations, data exchange, residual learning, and deeper layers with increasing unit sizes. These innovations enable more accurate and stable approximations. Experimental results confirm that our models consistently outperform existing approaches by achieving lower mean squared errors and Error rates. Our best-performing model not only delivers reliable accuracy but also demonstrates strong robustness across various test ranges.
Förderung
- National Science and Technology Council, Taiwan
Zitieren
APA
Wu, C., & Shyu, S. J. (2026). Efficient Approximation of Goldbach Partition Function Using Machine Learning Models. IEEE Access, 14, 83095-83108. https://doi.org/10.1109/access.2026.3690991
Vancouver
Wu C, Shyu SJ. Efficient Approximation of Goldbach Partition Function Using Machine Learning Models. IEEE Access. 2026;14:83095-83108. doi:10.1109/access.2026.3690991
BibTeX
@article{Wu2026,
author = {Wu, Cheng-Zhe and Shyu, Shyong Jian},
title = {Efficient Approximation of Goldbach Partition Function Using Machine Learning Models},
journal = {IEEE Access},
year = {2026},
volume = {14},
pages = {83095--83108},
doi = {10.1109/access.2026.3690991}
}
EUVIMED