| dc.contributor.author | Savitsky, Jury | |
| dc.contributor.author | Golovko, Vladimir | |
| dc.coverage.spatial | Minsk | ru_RU |
| dc.coverage.spatial | Szczecin | ru_RU |
| dc.date.accessioned | 2023-11-15T13:43:58Z | |
| dc.date.available | 2023-11-15T13:43:58Z | |
| dc.date.issued | 1999 | |
| dc.identifier.citation | Savitsky, J. Training of the recurrent neural networks for prediction / J. Savitsky, V. Golovko // Pattern recognition and information processing : proceedings of Fifth International Cоnference, Minsk, 18–20 Мay 1999 / Belarusian state university of informatics and radioelectronics, Technical university of Szczecin [et. al] ; editors: Rauf Sadykhov [et al.]. –Minsk ; Szczecin, 1999. – Vol. 2. – P. 248–252 : il. – Bibliogr.: p. 252 (9 titles). | ru_RU |
| dc.identifier.uri | https://rep.bstu.by/handle/data/37092 | |
| dc.description | Савицкий Юрий, Головко Владимир. Обучение рекуррентных нейронных сетей для прогнозирования | ru_RU |
| dc.description.abstract | In this paper the technique of creation of effective methods of training recurrent neural network for prediction problems are discussed. The various functions of activation of neural units are considered. The adaptive algorithms of training of neural networks with varied functions of activation of neural elements are considered. The computing experiments on prediction of time series demonstrate possibilities of the developed methods. | ru_RU |
| dc.language.iso | en | ru_RU |
| dc.publisher | BSUIR | ru_RU |
| dc.subject | recurrent neural network | ru_RU |
| dc.subject | рекуррентная нейронная сеть | ru_RU |
| dc.subject | prediction | ru_RU |
| dc.subject | прогнозирование | ru_RU |
| dc.title | Training of the recurrent neural networks for prediction | ru_RU |
| dc.title.alternative | Обучение рекуррентных нейронных сетей для прогнозирования | ru_RU |
| dc.type | Научный доклад (Working Paper) | ru_RU |
