Neuroevolutionary reinforcing learning of neural networks

The article presents the results of combining 4 different types of neural network learning: evolutionary, reinforcing, deep and extrapolating. The last two are used as the primary method for reducing the dimension of the input signal of the system and simplifying the process of its training in terms...

Full description

Saved in:
Bibliographic Details
Main Authors: Y. A. Bury, D. I. Samal
Format: Article
Language:English
Published: Belarusian National Technical University 2022-01-01
Series:Системный анализ и прикладная информатика
Subjects:
Online Access:https://sapi.bntu.by/jour/article/view/534
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832557385733898240
author Y. A. Bury
D. I. Samal
author_facet Y. A. Bury
D. I. Samal
author_sort Y. A. Bury
collection DOAJ
description The article presents the results of combining 4 different types of neural network learning: evolutionary, reinforcing, deep and extrapolating. The last two are used as the primary method for reducing the dimension of the input signal of the system and simplifying the process of its training in terms of computational complexity.In the presented work, the neural network structure of the control device of the modeled system is formed in the course of the evolutionary process, taking into account the currently known structural and developmental features of self-learning systems that take place in living nature. This method of constructing it makes it possible to bypass the specific limitations of models created on the basis of recombination of already known topologies of neural networks.
format Article
id doaj-art-82845d0fc3044e05ab4063e5b2a28c89
institution Kabale University
issn 2309-4923
2414-0481
language English
publishDate 2022-01-01
publisher Belarusian National Technical University
record_format Article
series Системный анализ и прикладная информатика
spelling doaj-art-82845d0fc3044e05ab4063e5b2a28c892025-02-03T05:16:54ZengBelarusian National Technical UniversityСистемный анализ и прикладная информатика2309-49232414-04812022-01-0104162410.21122/2309-4923-2021-4-16-24400Neuroevolutionary reinforcing learning of neural networksY. A. Bury0D. I. Samal1Belarusian State University of Informatics and RadioelectronicsBelarusian State University of Informatics and RadioelectronicsThe article presents the results of combining 4 different types of neural network learning: evolutionary, reinforcing, deep and extrapolating. The last two are used as the primary method for reducing the dimension of the input signal of the system and simplifying the process of its training in terms of computational complexity.In the presented work, the neural network structure of the control device of the modeled system is formed in the course of the evolutionary process, taking into account the currently known structural and developmental features of self-learning systems that take place in living nature. This method of constructing it makes it possible to bypass the specific limitations of models created on the basis of recombination of already known topologies of neural networks.https://sapi.bntu.by/jour/article/view/534neural networksconvolution neural networkneuroevolutionevolutionary algorithmsgenetic algorithmimage recognitioncharacter recognitiontext recognitionneural network trainingdeep learningreinforcement learning
spellingShingle Y. A. Bury
D. I. Samal
Neuroevolutionary reinforcing learning of neural networks
Системный анализ и прикладная информатика
neural networks
convolution neural network
neuroevolution
evolutionary algorithms
genetic algorithm
image recognition
character recognition
text recognition
neural network training
deep learning
reinforcement learning
title Neuroevolutionary reinforcing learning of neural networks
title_full Neuroevolutionary reinforcing learning of neural networks
title_fullStr Neuroevolutionary reinforcing learning of neural networks
title_full_unstemmed Neuroevolutionary reinforcing learning of neural networks
title_short Neuroevolutionary reinforcing learning of neural networks
title_sort neuroevolutionary reinforcing learning of neural networks
topic neural networks
convolution neural network
neuroevolution
evolutionary algorithms
genetic algorithm
image recognition
character recognition
text recognition
neural network training
deep learning
reinforcement learning
url https://sapi.bntu.by/jour/article/view/534
work_keys_str_mv AT yabury neuroevolutionaryreinforcinglearningofneuralnetworks
AT disamal neuroevolutionaryreinforcinglearningofneuralnetworks