Buchumschlag

Neural networks’ learning process acceleration

This study is devoted to evaluating the process of training of a parallel system in the form of an artificial neural network, which is built using a genetic algorithm. The methods that allow to achieve this goal are computer simulation of a neural network on multi-core CPUs and a genetic algorithm f...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:PROBLEMS IN PROGRAMMING
Datum:2020
Heft:2-3
Сторінки:313-321
ISSN:1727-4907
Автори та афіліації:
  • L. Katerynych — Kiev Taras Shevchenko National University
  • M.M. Veres — Kiev Taras Shevchenko National University — ORCID: 0000-0002-8512-5560
  • E. Safarov — Kiev Taras Shevchenko National University — ORCID: 0000-0001-9651-4679
Hauptverfasser: Katerynych, L., Veres, M.M., Safarov, E.
Format: Artikel
Sprache:Englisch
Veröffentlicht: PROBLEMS IN PROGRAMMING 2020
Schlagworte:
multi-core CPUs
artificial neural networks
artificial neuron
genetic algorithm
selection
crossing
mutation
parallel computing
UDC 004.4
Online Zugang:https://pp.isofts.kiev.ua/index.php/ojs1/article/view/423
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Назва журналу:Problems in programming
Завантажити файл: Pdf

Institution

Problems in programming
Beschreibung
Zusammenfassung:This study is devoted to evaluating the process of training of a parallel system in the form of an artificial neural network, which is built using a genetic algorithm. The methods that allow to achieve this goal are computer simulation of a neural network on multi-core CPUs and a genetic algorithm for finding the weights of an artificial neural network. The performance of sequential and parallel training processes of artificial neural network is compared.Problems in programming 2020; 2-3: 313-321
ISSN:1727-4907
DOI:10.15407/pp2020.02-03.313

Ähnliche Einträge