| dc.contributor.author | Golovko, Vladimir | |
| dc.contributor.author | Maniakov, Nikolaj | |
| dc.contributor.author | Makhnist, Leonid | |
| dc.coverage.spatial | Lviv | ru_RU |
| dc.date.accessioned | 2023-12-06T08:18:04Z | |
| dc.date.available | 2023-12-06T08:18:04Z | |
| dc.date.issued | 2003 | |
| dc.identifier.citation | Golovko, V. Multilayer Neural Networks Training Methodic / Vladimir Golovko, Nikolaj Maniakov, Leonid Makhnist // Proceeding of the Second IEEE International Workshop on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications : IDAACS’2003, Lviv, September 8–10, 2003 / Institute of computer information technologies [et. al]. – Lviv : Lviv polytechnic, 2003. – P. 185–190. – Bibliogr.: p. 190 (6 titles). | ru_RU |
| dc.identifier.uri | https://rep.bstu.by/handle/data/37552 | |
| dc.description | Головко Владимир Адамович, Маньяков Николай Владимирович, Махнист Леонид Петрович. Методика обучения многослойных нейронных сетей | ru_RU |
| dc.description.abstract | Is proposed three new techniques for training of jnpUt vector If is defined as' multilayer neural networks. Its basic concept is based on the gradient descent method. For every methodic are showed formulas for calculation of the adaptive training steps. Matrix algorithmization for all of this techniques are very helpful in its program realization. | ru_RU |
| dc.language.iso | en | ru_RU |
| dc.publisher | Lviv polytechnic | ru_RU |
| dc.subject | multilayer neural networks | ru_RU |
| dc.subject | многослойные нейронные сети | ru_RU |
| dc.subject | gradient descent method | ru_RU |
| dc.subject | метод градиентного спуска | ru_RU |
| dc.subject | adaptive training step | ru_RU |
| dc.subject | этап адаптивного обучения | ru_RU |
| dc.title | Multilayer Neural Networks Training Methodic | ru_RU |
| dc.title.alternative | Методика обучения многослойных нейронных сетей | ru_RU |
| dc.type | Научный доклад (Working Paper) | ru_RU |
