EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Fractional Optimizers Meet Fractal Activation Functions: An Empirical Study of Multi-Scale Optimization in Neural Networks

Sebastian Raubitzek, Georg Goldenits, Sebastian Schrittwieser, Philip König, Kevin Mallinger

Fractal and Fractional · 08.11.2026 · 10 (11) · 780

DOI: 10.3390/fractalfract10110780 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Fractal and Fractional, online erschienen am 08.11.2026. Verfasst von Sebastian Raubitzek und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Christian Doppler Research Association, Austrian Research Promotion Agency.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Fractional optimization methods and fractal activation functions are two independent directions for improving neural network training. Fractional optimizers extend first-order optimization through fractional derivatives and memory effects, whereas fractal activations introduce multi-scale nonlinear representations based on self-similar Weierstrass- and Blancmange-type functions. Here, we investigate their interaction within a unified experimental framework. We evaluate fractional optimizer families on Ackley and Himmelblau benchmark surfaces, in standard form and with additive Weierstrass-type perturbations, and then in feed-forward neural networks with conventional and fractal activations on ten classification datasets. The comparison includes standard methods, Herrera-type local scaling optimizers, explicit and adaptive memory-based fractional optimizers, and other representative literature methods. Fractional optimization and fractal activations show useful but selective pairings. Herrera-type local fractional scaling performs well with selected fractal activations in network training, while explicit Grünwald–Letnikov memory is competitive on the controlled surfaces without being preferentially favoured by the perturbation: the unmodified baselines rank first on both additive variants. Adaptive memory improves plain memory substitution in several cases, supporting controlled fractional memory as a promising direction rather than a universal replacement.

Förderung

  • Christian Doppler Research Association
  • Austrian Research Promotion Agency

Zitieren

APA

Raubitzek, S., Goldenits, G., Schrittwieser, S., König, P., & Mallinger, K. (2026). Fractional Optimizers Meet Fractal Activation Functions: An Empirical Study of Multi-Scale Optimization in Neural Networks. Fractal and Fractional, 10(11), 780. https://doi.org/10.3390/fractalfract10110780

Vancouver

Raubitzek S, Goldenits G, Schrittwieser S, König P, Mallinger K. Fractional Optimizers Meet Fractal Activation Functions: An Empirical Study of Multi-Scale Optimization in Neural Networks. Fractal and Fractional. 2026;10(11):780. doi:10.3390/fractalfract10110780

BibTeX
@article{Raubitzek2026,
  author = {Raubitzek, Sebastian and Goldenits, Georg and Schrittwieser, Sebastian and König, Philip and Mallinger, Kevin},
  title = {Fractional Optimizers Meet Fractal Activation Functions: An Empirical Study of Multi-Scale Optimization in Neural Networks},
  journal = {Fractal and Fractional},
  year = {2026},
  volume = {10},
  number = {11},
  pages = {780},
  doi = {10.3390/fractalfract10110780}
}
Kostenlos starten →