Work

On the evolution of recurrent neural systems

Year: 2024

Type: article

Abstract: 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.

Source: System research and information technologies

DOI: 10.20535/srit.2308-8893.2024.4.06

Authors: Gennadii Abramov, Ivan Gushchin, Tetiana Sirenka

Institutions: Kherson State Maritime Academy, V. N. Karazin Kharkiv National University

Language: English

Topic: Neural Networks and Applications

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: diamond

OpenAlex ID: W4408189302

FWCI: 0.304

Cites:

Cited by: 2

Related to: 10