Saved in:
Bibliographic Details
Main Author: Mihara, Tomoki
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.29905
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917375295619072
author Mihara, Tomoki
author_facet Mihara, Tomoki
contents We propose a new frame work of $p$-adic neural network. Unlike the original $p$-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 $p$-adic character on the topological Abelian group $\mathbb{Z}_p$ of $p$-adic integers as an activation function. We prove the $p$-adic universal approximation theorem for this formulation of $p$-adic neural network, and reduce it to the feasibility problem of polynomial equations over the finite ring of integers modulo a power of $p$.
format Preprint
id arxiv_https___arxiv_org_abs_2603_29905
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle $p$-adic Character Neural Network
Mihara, Tomoki
Number Theory
Machine Learning
We propose a new frame work of $p$-adic neural network. Unlike the original $p$-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 $p$-adic character on the topological Abelian group $\mathbb{Z}_p$ of $p$-adic integers as an activation function. We prove the $p$-adic universal approximation theorem for this formulation of $p$-adic neural network, and reduce it to the feasibility problem of polynomial equations over the finite ring of integers modulo a power of $p$.
title $p$-adic Character Neural Network
topic Number Theory
Machine Learning
url https://arxiv.org/abs/2603.29905