Noncommutative $C^*$-algebra Net: Learning Neural Networks with Powerful Product Structure in $C^*$-algebra

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Hataya, Ryuichiro, Hashimoto, Yuka
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911946068983808
author Hataya, Ryuichiro
Hashimoto, Yuka
author_facet Hataya, Ryuichiro
Hashimoto, Yuka
contents We propose a new generalization of neural network parameter spaces with noncommutative $C^*$-algebra, which possesses a rich noncommutative structure of products. We show that this noncommutative structure induces powerful effects in learning neural networks. Our framework has a wide range of applications, such as learning multiple related neural networks simultaneously with interactions and learning equivariant features with respect to group actions. Numerical experiments illustrate the validity of our framework and its potential power.
format Preprint
id arxiv_https___arxiv_org_abs_2302_01191
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Noncommutative $C^*$-algebra Net: Learning Neural Networks with Powerful Product Structure in $C^*$-algebra
Hataya, Ryuichiro
Hashimoto, Yuka
Operator Algebras
Machine Learning
Functional Analysis
We propose a new generalization of neural network parameter spaces with noncommutative $C^*$-algebra, which possesses a rich noncommutative structure of products. We show that this noncommutative structure induces powerful effects in learning neural networks. Our framework has a wide range of applications, such as learning multiple related neural networks simultaneously with interactions and learning equivariant features with respect to group actions. Numerical experiments illustrate the validity of our framework and its potential power.
title Noncommutative $C^*$-algebra Net: Learning Neural Networks with Powerful Product Structure in $C^*$-algebra
topic Operator Algebras
Machine Learning
Functional Analysis
url https://arxiv.org/abs/2302.01191