Neural Network Operator-Based Fractal Approximation: Smoothness Preservation and Convergence Analysis

Abstract:This paper introduces the construction of fractal interpolation functions (FIFs), whose graphs are the attractors of an iterated function system (IFS). Integrating concepts from approximation theory, $\alpha$-fractal functions are constructed, employing shallow neural network operators. Based on the same methodology, we developed fractal interpolation functions using only discrete function values, unlike traditional methods that require each value of the target function. In order to preserve the smoothness of the target function, a method for constructing such FIFs is introduced, employing four-layered neural network operators, i.e., whenever $f \in C^{r}[a,b]$, the corresponding FIF $f^{\alpha} \in C^{r}[a,b]$. This work uses key approximation theory tools, such as the modulus of continuity and interpolation operators, to develop convergence results and uniform approximation error bounds. To validate the theoretical results obtained, numerical experiments with graphical analysis using Python is provided.

Machine Learning (cs.LG); Numerical Analysis (math.NA)

arXiv:2505.06229 [cs.LG]

(or arXiv:2505.06229v2 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2505.06229 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.