Deep Neural Networks: A Formulation Via Non-Archimedean Analysis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Zúñiga-Galindo, W. A.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912986962067456
author Zúñiga-Galindo, W. A.
author_facet Zúñiga-Galindo, W. A.
contents We introduce a new class of deep neural networks (DNNs) with multilayered tree-like architectures. The architectures are codified using numbers from the ring of integers of non-Archimdean 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.
format Preprint
id arxiv_https___arxiv_org_abs_2402_00094
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Deep Neural Networks: A Formulation Via Non-Archimedean Analysis
Zúñiga-Galindo, W. A.
Neural and Evolutionary Computing
Artificial Intelligence
Machine Learning
Primary 68T07, 65D15, Secondary 41A30, 11S85
We introduce a new class of deep neural networks (DNNs) with multilayered tree-like architectures. The architectures are codified using numbers from the ring of integers of non-Archimdean 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.
title Deep Neural Networks: A Formulation Via Non-Archimedean Analysis
topic Neural and Evolutionary Computing
Artificial Intelligence
Machine Learning
Primary 68T07, 65D15, Secondary 41A30, 11S85
url https://arxiv.org/abs/2402.00094