Cover Image

The Alexander-Hirschowitz theorem for neurovarieties

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Massarenti, A., Mella, M.
Format:	Preprint
Published:	2025
Subjects:	Algebraic Geometry Artificial Intelligence Machine Learning Commutative Algebra Primary 14N07, Secondary 14N05, 14N15
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866908673243086848
author	Massarenti, A. Mella, M.
author_facet	Massarenti, A. Mella, M.
contents	We study neurovarieties for polynomial neural networks and fully characterize when they attain the expected dimension in the single-output case. As consequences, we establish non-defectiveness and global identifiability for multi-output architectures.
format	Preprint
id	arxiv_https___arxiv_org_abs_2511_19703
institution	arXiv
publishDate	2025
record_format	arxiv
spellingShingle	The Alexander-Hirschowitz theorem for neurovarieties Massarenti, A. Mella, M. Algebraic Geometry Artificial Intelligence Machine Learning Commutative Algebra Primary 14N07, Secondary 14N05, 14N15 We study neurovarieties for polynomial neural networks and fully characterize when they attain the expected dimension in the single-output case. As consequences, we establish non-defectiveness and global identifiability for multi-output architectures.
title	The Alexander-Hirschowitz theorem for neurovarieties
topic	Algebraic Geometry Artificial Intelligence Machine Learning Commutative Algebra Primary 14N07, Secondary 14N05, 14N15
url	https://arxiv.org/abs/2511.19703