Journal of Fourier Analysis and Applications Analysis

Deep Neural Networks: A Formulation via Non-Archimedean Analysis

W. A. Zúñiga-Galindo
Springer Nature · 2026-07-27 · DOI 10.1007/s00041-026-10290-y

Abstract

Abstract We introduce a new class of deep neural networks (DNNs) with multilayered tree-like architectures. The architectures are codified by using numbers in the ring of integers of non-Archimedean local fields. These rings have a natural hierarchical organization as infinite rooted trees. Natural morphisms on these rings allow us to construct finite multilayered architectures. The new DNNs are robust universal approximators of real-valued functions defined on the mentioned rings. We also show that the DNNs are robust universal approximators of real-valued square-integrable functions defined in the unit interval.

Read at publisher →