Nonnegative Tensor Decomposition Via Collaborative Neurodynamic Optimization

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ahmadi-Asl, Salman, Leplat, Valentin, Phan, Anh-Huy, Cichocki, Andrzej
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917881903579136
author Ahmadi-Asl, Salman
Leplat, Valentin
Phan, Anh-Huy
Cichocki, Andrzej
author_facet Ahmadi-Asl, Salman
Leplat, Valentin
Phan, Anh-Huy
Cichocki, Andrzej
contents This paper introduces a novel collaborative neurodynamic model for computing nonnegative Canonical Polyadic Decomposition (CPD). The model relies on a system of recurrent neural networks to solve the underlying nonconvex optimization problem associated with nonnegative CPD. Additionally, a discrete-time version of the continuous neural network is developed. To enhance the chances of reaching a potential global minimum, the recurrent neural networks are allowed to communicate and exchange information through particle swarm optimization (PSO). Convergence and stability analyses of both the continuous and discrete neurodynamic models are thoroughly examined. Experimental evaluations are conducted on random and real-world datasets to demonstrate the effectiveness of the proposed approach.
format Preprint
id arxiv_https___arxiv_org_abs_2411_18127
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Nonnegative Tensor Decomposition Via Collaborative Neurodynamic Optimization
Ahmadi-Asl, Salman
Leplat, Valentin
Phan, Anh-Huy
Cichocki, Andrzej
Numerical Analysis
This paper introduces a novel collaborative neurodynamic model for computing nonnegative Canonical Polyadic Decomposition (CPD). The model relies on a system of recurrent neural networks to solve the underlying nonconvex optimization problem associated with nonnegative CPD. Additionally, a discrete-time version of the continuous neural network is developed. To enhance the chances of reaching a potential global minimum, the recurrent neural networks are allowed to communicate and exchange information through particle swarm optimization (PSO). Convergence and stability analyses of both the continuous and discrete neurodynamic models are thoroughly examined. Experimental evaluations are conducted on random and real-world datasets to demonstrate the effectiveness of the proposed approach.
title Nonnegative Tensor Decomposition Via Collaborative Neurodynamic Optimization
topic Numerical Analysis
url https://arxiv.org/abs/2411.18127