Saved in:
Bibliographic Details
Main Authors: Jung, Inkee, Lau, Siu-Cheong
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.05492
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929693348855808
author Jung, Inkee
Lau, Siu-Cheong
author_facet Jung, Inkee
Lau, Siu-Cheong
contents In this paper,we develop a local-to-global and measure-theoretical approach to understand datasets. The idea is to take network models with restricted domains as local charts of datasets. We develop the mathematical foundations for these structures, and show in experiments how it can be used to find fuzzy domains and to improve accuracy in data classification problems.
format Preprint
id arxiv_https___arxiv_org_abs_2405_05492
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A logifold structure on measure space
Jung, Inkee
Lau, Siu-Cheong
Differential Geometry
Artificial Intelligence
Machine Learning
Probability
55N31, 53Z50, 68T07, 68T09, 60A10, 81P45, 94D05
In this paper,we develop a local-to-global and measure-theoretical approach to understand datasets. The idea is to take network models with restricted domains as local charts of datasets. We develop the mathematical foundations for these structures, and show in experiments how it can be used to find fuzzy domains and to improve accuracy in data classification problems.
title A logifold structure on measure space
topic Differential Geometry
Artificial Intelligence
Machine Learning
Probability
55N31, 53Z50, 68T07, 68T09, 60A10, 81P45, 94D05
url https://arxiv.org/abs/2405.05492