Artificial Neural Networks Multicriteria Training Based on Graphics Processors

Artificial Neural Networks Multicriteria Training Based on Graphics Processors

The report considers the task of training a multilayer perceptron, formulated as a problem of multiobjective optimization under uncertainty. To solve this problem, the principle of vector minimax was used. A parallel software implementation of a hierarchical evolutionary algorithm for solving a mult...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Engineering proceedings 2023-07, Vol.33 (1), p.57
Hauptverfasser: Vladimir A. Serov, Evgenia L. Dolgacheva, Elizaveta Y. Kosyuk, Daria L. Popova, Pavel P. Rogalev, Anastasia V. Tararina
Format: Artikel
Sprache:eng
Schlagworte:
artificial neural network
GPU
multicriteria optimization under uncertainty
parallel computing
vector minimax
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The report considers the task of training a multilayer perceptron, formulated as a problem of multiobjective optimization under uncertainty. To solve this problem, the principle of vector minimax was used. A parallel software implementation of a hierarchical evolutionary algorithm for solving a multicriteria optimization problem under uncertainty based on a GPU is presented.
ISSN:2673-4591
DOI:10.3390/engproc2023033057