On the evolution of recurrent neural systems

The evolution of neural network architectures, first of the recurrent type and then with the use of attention technology, is considered. It shows how the approaches changed and how the developers’ experience was enriched. It is important that the neural networks themselves learn to understand the de...

Full description

Saved in:
Bibliographic Details
Main Authors: Gennadii Abramov, Ivan Gushchin, Tetiana Sirenka
Format: Article
Language:Ukrainian
Published: Igor Sikorsky Kyiv Polytechnic Institute 2024-12-01
Series:Sistemnì Doslìdženâ ta Informacìjnì Tehnologìï
Subjects:
Online Access:http://journal.iasa.kpi.ua/article/view/322523
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849324613824151552
author Gennadii Abramov
Ivan Gushchin
Tetiana Sirenka
author_facet Gennadii Abramov
Ivan Gushchin
Tetiana Sirenka
author_sort Gennadii Abramov
collection DOAJ
description The evolution of neural network architectures, first of the recurrent type and then with the use of attention technology, is considered. It shows how the approaches changed and how the developers’ experience was enriched. It is important that the neural networks themselves learn to understand the developers’ intentions and actually correct errors and flaws in technologies and architectures. Using new active elements instead of neurons expanded the scope of connectionist networks. It led to the emergence of new structures — Kolmogorov–Arnold Networks (KANs), which may become serious competitors to networks with artificial neurons.
format Article
id doaj-art-3dda28e352a2423490f86d48531f2713
institution Kabale University
issn 1681-6048
2308-8893
language Ukrainian
publishDate 2024-12-01
publisher Igor Sikorsky Kyiv Polytechnic Institute
record_format Article
series Sistemnì Doslìdženâ ta Informacìjnì Tehnologìï
spelling doaj-art-3dda28e352a2423490f86d48531f27132025-08-20T03:48:41ZukrIgor Sikorsky Kyiv Polytechnic InstituteSistemnì Doslìdženâ ta Informacìjnì Tehnologìï1681-60482308-88932024-12-014778510.20535/SRIT.2308-8893.2024.4.06361238On the evolution of recurrent neural systemsGennadii Abramov0https://orcid.org/0000-0003-0333-8819Ivan Gushchin1https://orcid.org/0000-0002-1917-716XTetiana Sirenka2Kherson State Maritime Academy, KhersonV. N. Karazin Kharkiv National University, KharkivV. N. Karazin Kharkiv National University, KharkivThe evolution of neural network architectures, first of the recurrent type and then with the use of attention technology, is considered. It shows how the approaches changed and how the developers’ experience was enriched. It is important that the neural networks themselves learn to understand the developers’ intentions and actually correct errors and flaws in technologies and architectures. Using new active elements instead of neurons expanded the scope of connectionist networks. It led to the emergence of new structures — Kolmogorov–Arnold Networks (KANs), which may become serious competitors to networks with artificial neurons.http://journal.iasa.kpi.ua/article/view/322523recurrent neural networkstransformer technologykans
spellingShingle Gennadii Abramov
Ivan Gushchin
Tetiana Sirenka
On the evolution of recurrent neural systems
Sistemnì Doslìdženâ ta Informacìjnì Tehnologìï
recurrent neural networks
transformer technology
kans
title On the evolution of recurrent neural systems
title_full On the evolution of recurrent neural systems
title_fullStr On the evolution of recurrent neural systems
title_full_unstemmed On the evolution of recurrent neural systems
title_short On the evolution of recurrent neural systems
title_sort on the evolution of recurrent neural systems
topic recurrent neural networks
transformer technology
kans
url http://journal.iasa.kpi.ua/article/view/322523
work_keys_str_mv AT gennadiiabramov ontheevolutionofrecurrentneuralsystems
AT ivangushchin ontheevolutionofrecurrentneuralsystems
AT tetianasirenka ontheevolutionofrecurrentneuralsystems