Отрывок: This result could not be appreciated as convenient for practice. The goal of the paper is to increase the quality of training Kohonen neural networks and ANN based on such a type. The general model of the considered ANN is described in [1] and looks like 2- dimensional modification of the Kohonen and Wilshaw and von der Malsburg network. This kind of ANN is used to creat...
Полная запись метаданных
Поле DC | Значение | Язык |
---|---|---|
dc.contributor.author | Rozenberg, Y.N. | - |
dc.contributor.author | Olshansky, A.М. | - |
dc.contributor.author | Dovgerd, I.А. | - |
dc.contributor.author | Dovgerd, G.А. | - |
dc.contributor.author | Ignatenkov, A.V. | - |
dc.contributor.author | Ignatenkov, P.V. | - |
dc.date.accessioned | 2020-07-31 11:36:57 | - |
dc.date.available | 2020-07-31 11:36:57 | - |
dc.date.issued | 2020 | - |
dc.identifier | Dspace\SGAU\20200730\84860 | ru |
dc.identifier.citation | Rozenberg Y.N. Some approaches of improving the quality of artificial neural network training / Y.N. Rozenberg, A.М. Olshansky, I.А. Dovgerd, G.А. Dovgerd, A.V. Ignatenkov, P.V. Ignatenkov // Информационные технологии и нанотехнологии (ИТНТ-2020). Сборник трудов по материалам VI Международной конференции и молодежной школы (г. Самара, 26-29 мая): в 4 т. / Самар. нац.-исслед. ун-т им. С. П. Королева (Самар. ун-т), Ин-т систем. обраб. изобр. РАН-фил. ФНИЦ "Кристаллография и фотоника" РАН; [под ред. В. А. Фурсова]. – Самара: Изд-во Самар. ун-та, 2020. – Том 4. Науки о данных. – 2020. – С. 240-242. | ru |
dc.identifier.uri | http://repo.ssau.ru/handle/Informacionnye-tehnologii-i-nanotehnologii/Some-approaches-of-improving-the-quality-of-artificial-neural-network-training-84860 | - |
dc.description.abstract | The paper is devoted to a problem of regular improving the quality of artificial neural network (ANN) training. The object of study is a complex neural network which consists of 2-dimensional Kohonen network and Wilshaw and von der Malsburg network. These networks are applied to a timetable problem for transport systems. The main existing results of using optimal control theory for ANN training are analyzed; authors suggest a new technique based on the direct neural control. Authors give comparative values of error during a training process for the traditional methods and a new approach. It is presented that this new technique is better than the traditional one for considered neural networks. | ru |
dc.language.iso | en_US | ru |
dc.title | Some approaches of improving the quality of artificial neural network training | ru |
dc.type | Article | ru |
dc.textpart | This result could not be appreciated as convenient for practice. The goal of the paper is to increase the quality of training Kohonen neural networks and ANN based on such a type. The general model of the considered ANN is described in [1] and looks like 2- dimensional modification of the Kohonen and Wilshaw and von der Malsburg network. This kind of ANN is used to creat... | - |
Располагается в коллекциях: | Информационные технологии и нанотехнологии |
Файлы этого ресурса:
Файл | Описание | Размер | Формат | |
---|---|---|---|---|
ИТНТ-2020_том 4-240-242.pdf | 334.96 kB | Adobe PDF | Просмотреть/Открыть |
Показать базовое описание ресурса
Просмотр статистики
Поделиться:
Все ресурсы в архиве электронных ресурсов защищены авторским правом, все права сохранены.