Neural networks art: solving problems with multiple solutions and new teaching algorithm

dc.contributor.author	Dmitrienko, V. D.	en
dc.contributor.author	Zakovorotnyi, A. Yu.	en
dc.contributor.author	Leonov, S. Yu.	en
dc.contributor.author	Khavina, I. P.	en
dc.date.accessioned	2020-04-09T09:24:21Z
dc.date.available	2020-04-09T09:24:21Z
dc.date.issued	2014
dc.description.abstract	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.	en
dc.identifier.citation	Neural networks art: solving problems with multiple solutions and new teaching algorithm [Electronic resource] / V. D. Dmitrienko [et al.] // The Open Neurology Journal. – Electronic text data. – 2014. – Vol. 8. – P. 15-21. – Access mode: https://openneurologyjournal.com/contents/volumes/V8/TONEUJ-8-15/TONEUJ-8-15.pdf, вільний (дата звернення 09.04.2020 р.)	en
dc.identifier.doi	doi.org/10.2174/1874205X01408010015
dc.identifier.uri	https://repository.kpi.kharkov.ua/handle/KhPI-Press/45514
dc.language.iso	en
dc.subject	degradation of breeding classes	en
dc.subject	learning algorithms	en
dc.subject	neural network adaptive resonance theory	en
dc.subject	problems with multiple solutions	en
dc.title	Neural networks art: solving problems with multiple solutions and new teaching algorithm	en
dc.type	Article	en

Файли

Зараз показуємо 1 - 1 з 1

Зараз показуємо 1 - 1 з 1