$p$-adic Character Neural Network
Number Theory
2026-04-01 v1 Machine Learning
Abstract
We propose a new frame work of -adic neural network. Unlike the original -adic neural network by S.\ Albeverio, A.\ Khrennikov, and B.\ Tirrozi using a family of characteristic functions indexed by hyperparameters of precision as activation functions, we use a single injective -adic character on the topological Abelian group of -adic integers as an activation function. We prove the -adic universal approximation theorem for this formulation of -adic neural network, and reduce it to the feasibility problem of polynomial equations over the finite ring of integers modulo a power of .
Keywords
Cite
@article{arxiv.2603.29905,
title = {$p$-adic Character Neural Network},
author = {Tomoki Mihara},
journal= {arXiv preprint arXiv:2603.29905},
year = {2026}
}