| DC Field | Value | Language |
|---|
| dc.contributor.author | Gasitashvili, Z. | - |
| dc.contributor.author | Phkhovelishvili, M. | - |
| dc.contributor.author | Archvadze, N. | - |
| dc.date.accessioned | 2021-11-04T08:39:24Z | - |
| dc.date.available | 2021-11-04T08:39:24Z | - |
| dc.date.issued | 2021 | - |
| dc.identifier.citation | Gasitashvili, Z. New Algorithm for Building Effective Model from Prediction Models Using Parallel Data / Gasitashvili Z., Phkhovelishvili M., Archvadze N. // Pattern Recognition and Information Processing (PRIP'2021) = Распознавание образов и обработка информации (2021) : Proceedings of the 15th International Conference, 21–24 Sept. 2021, Minsk, Belarus / United Institute of Informatics Problems of the National Academy of Sciences of Belarus. – Minsk, 2021. – P. 25–28. | ru_RU |
| dc.identifier.uri | https://libeldoc.bsuir.by/handle/123456789/45795 | - |
| dc.description.abstract | Building much more effective new hybrid models from prediction models, using parallel data is discussed. The algorithm for selection of model pairs and its advantage over any best prediction model is provided. The advantage of prediction models with higher number of pairs over lower number of pairs is shown and the algorithm of taking into consideration the “approximate coincidence” of predictions is discussed when selecting pairs. | ru_RU |
| dc.language.iso | en | ru_RU |
| dc.publisher | UIIP NASB | ru_RU |
| dc.subject | материалы конференций | ru_RU |
| dc.subject | conference proceedings | ru_RU |
| dc.subject | parallel data | ru_RU |
| dc.subject | prediction models | ru_RU |
| dc.subject | approximate accuracy | ru_RU |
| dc.subject | probablity of prediction success | ru_RU |
| dc.title | New Algorithm for Building Effective Model from Prediction Models Using Parallel Data | ru_RU |
| dc.type | Статья | ru_RU |
| Appears in Collections: | Pattern Recognition and Information Processing (PRIP'2021) = Распознавание образов и обработка информации (2021)
|
