Linear Independence of Generalized Neurons and Related Functions

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Zhang, Leyang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910634307747840
author Zhang, Leyang
author_facet Zhang, Leyang
contents The linear independence of neurons plays a significant role in theoretical analysis of neural networks. Specifically, given neurons $H_1, ..., H_n: \bR^N \times \bR^d \to \bR$, we are interested in the following question: when are $\{H_1(θ_1, \cdot), ..., H_n(θ_n, \cdot)\}$ are linearly independent as the parameters $θ_1, ..., θ_n$ of these functions vary over $\bR^N$. Previous works give a complete characterization of two-layer neurons without bias, for generic smooth activation functions. In this paper, we study the problem for neurons with arbitrary layers and widths, giving a simple but complete characterization for generic analytic activation functions.
format Preprint
id arxiv_https___arxiv_org_abs_2410_03693
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Linear Independence of Generalized Neurons and Related Functions
Zhang, Leyang
Machine Learning
The linear independence of neurons plays a significant role in theoretical analysis of neural networks. Specifically, given neurons $H_1, ..., H_n: \bR^N \times \bR^d \to \bR$, we are interested in the following question: when are $\{H_1(θ_1, \cdot), ..., H_n(θ_n, \cdot)\}$ are linearly independent as the parameters $θ_1, ..., θ_n$ of these functions vary over $\bR^N$. Previous works give a complete characterization of two-layer neurons without bias, for generic smooth activation functions. In this paper, we study the problem for neurons with arbitrary layers and widths, giving a simple but complete characterization for generic analytic activation functions.
title Linear Independence of Generalized Neurons and Related Functions
topic Machine Learning
url https://arxiv.org/abs/2410.03693