Saved in:
Bibliographic Details
Main Authors: Chiantini, Luca, D'Inverno, Giuseppe Alessio, Marziali, Sara
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.06768
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909606552272896
author Chiantini, Luca
D'Inverno, Giuseppe Alessio
Marziali, Sara
author_facet Chiantini, Luca
D'Inverno, Giuseppe Alessio
Marziali, Sara
contents Any kind of network can be naturally represented by a Directed Acyclic Graph (DAG); additionally, activation functions can determine the reaction of each node of the network with respect to the signal(s) incoming. We study the characterization of the signal distribution in a network under the lens of tensor algebra. More specifically, we describe every activation function as tensor distributions with respect to the nodes, called \textit{activation tensors}. The distribution of the signal is encoded in the \textit{total tensor} of the network. We formally prove that the total tensor can be obtained by computing the \textit{Batthacharya-Mesner Product} (BMP), an $n$-ary operation for tensors of order $n$, on the set of the activation tensors properly ordered and processed via two basic operations, that we call \textit{blow} and \textit{forget}. Our theoretical framework can be validated through the related code developed in Python.
format Preprint
id arxiv_https___arxiv_org_abs_2402_06768
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Product of Tensors and Description of Networks
Chiantini, Luca
D'Inverno, Giuseppe Alessio
Marziali, Sara
Algebraic Geometry
Any kind of network can be naturally represented by a Directed Acyclic Graph (DAG); additionally, activation functions can determine the reaction of each node of the network with respect to the signal(s) incoming. We study the characterization of the signal distribution in a network under the lens of tensor algebra. More specifically, we describe every activation function as tensor distributions with respect to the nodes, called \textit{activation tensors}. The distribution of the signal is encoded in the \textit{total tensor} of the network. We formally prove that the total tensor can be obtained by computing the \textit{Batthacharya-Mesner Product} (BMP), an $n$-ary operation for tensors of order $n$, on the set of the activation tensors properly ordered and processed via two basic operations, that we call \textit{blow} and \textit{forget}. Our theoretical framework can be validated through the related code developed in Python.
title Product of Tensors and Description of Networks
topic Algebraic Geometry
url https://arxiv.org/abs/2402.06768