Neural Networks Art: Solving Problems with Multiple Solutions and New Teaching Algorithm

A new discrete neural networks adaptive resonance theory (ART), which allows solving problems with multiple solutions, is developed. New algorithms neural networks teaching ART to prevent degradation and reproduction classes at training noisy input data is developed. Proposed learning algorithms dis...

Descripción completa

Detalles Bibliográficos
Autores principales: Dmitrienko, V. D, Zakovorotnyi, A. Yu., Leonov, S. Yu., Khavina, I. P
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Bentham Open 2014
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4168651/
https://www.ncbi.nlm.nih.gov/pubmed/25246988
http://dx.doi.org/10.2174/1874205X01408010015
_version_ 1782335590432243712
author Dmitrienko, V. D
Zakovorotnyi, A. Yu.
Leonov, S. Yu.
Khavina, I. P
author_facet Dmitrienko, V. D
Zakovorotnyi, A. Yu.
Leonov, S. Yu.
Khavina, I. P
author_sort Dmitrienko, V. D
collection PubMed
description A new discrete neural networks adaptive resonance theory (ART), which allows solving problems with multiple solutions, is developed. New algorithms neural networks teaching ART to prevent degradation and reproduction classes at training noisy input data is developed. Proposed learning algorithms discrete ART networks, allowing obtaining different classification methods of input.
format Online
Article
Text
id pubmed-4168651
institution National Center for Biotechnology Information
language English
publishDate 2014
publisher Bentham Open
record_format MEDLINE/PubMed
spelling pubmed-41686512014-09-22 Neural Networks Art: Solving Problems with Multiple Solutions and New Teaching Algorithm Dmitrienko, V. D Zakovorotnyi, A. Yu. Leonov, S. Yu. Khavina, I. P Open Neurol J Article A new discrete neural networks adaptive resonance theory (ART), which allows solving problems with multiple solutions, is developed. New algorithms neural networks teaching ART to prevent degradation and reproduction classes at training noisy input data is developed. Proposed learning algorithms discrete ART networks, allowing obtaining different classification methods of input. Bentham Open 2014-09-9 /pmc/articles/PMC4168651/ /pubmed/25246988 http://dx.doi.org/10.2174/1874205X01408010015 Text en © Dmitrienko et al.; Licensee Bentham Open. http://creativecommons.org/licenses/by-nc/3.0/ This is an open access article licensed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0/) which permits unrestricted, non-commercial use, distribution and reproduction in any medium, provided the work is properly cited.
spellingShingle Article
Dmitrienko, V. D
Zakovorotnyi, A. Yu.
Leonov, S. Yu.
Khavina, I. P
Neural Networks Art: Solving Problems with Multiple Solutions and New Teaching Algorithm
title Neural Networks Art: Solving Problems with Multiple Solutions and New Teaching Algorithm
title_full Neural Networks Art: Solving Problems with Multiple Solutions and New Teaching Algorithm
title_fullStr Neural Networks Art: Solving Problems with Multiple Solutions and New Teaching Algorithm
title_full_unstemmed Neural Networks Art: Solving Problems with Multiple Solutions and New Teaching Algorithm
title_short Neural Networks Art: Solving Problems with Multiple Solutions and New Teaching Algorithm
title_sort neural networks art: solving problems with multiple solutions and new teaching algorithm
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4168651/
https://www.ncbi.nlm.nih.gov/pubmed/25246988
http://dx.doi.org/10.2174/1874205X01408010015
work_keys_str_mv AT dmitrienkovd neuralnetworksartsolvingproblemswithmultiplesolutionsandnewteachingalgorithm
AT zakovorotnyiayu neuralnetworksartsolvingproblemswithmultiplesolutionsandnewteachingalgorithm
AT leonovsyu neuralnetworksartsolvingproblemswithmultiplesolutionsandnewteachingalgorithm
AT khavinaip neuralnetworksartsolvingproblemswithmultiplesolutionsandnewteachingalgorithm

Ejemplares similares