Using the Out-Of-Bag Model in the Cross-Validation Procedure Научная публикация
Журнал |
Pattern Recognition and Image Analysis
ISSN: 1054-6618 , E-ISSN: 1555-6212 |
||
---|---|---|---|
Вых. Данные | Год: 2024, Том: 34, Номер: 4, Страницы: 1172-1176 Страниц : 5 DOI: 10.1134/S1054661824701232 | ||
Ключевые слова | machine learning, cross-validation, out-of-bag estimation, bias-variance decomposition, overfitting problem | ||
Авторы |
|
||
Организации |
|
Информация о финансировании (1)
1 | Институт математики им. С.Л. Соболева СО РАН | FWNF-2022-0015 |
Реферат:
In the widely known bagging method (random forest), an out-of-bag estimate is generated, which characterizes the quality of the constructed solution. This paper proposes to transfer the idea of constructing this assessment to the cross-validation procedure, which ultimately comes down to a change in the method for constructing the final solution. The resulting method has a smaller variance component in the corre sponding error decomposition. Another advantage is that the final solution uses the same models that were used to evaluate the quality during the cross-validation process. This can be particularly significant when the classification method uses significant randomization.
Библиографическая ссылка:
Nedel'ko V.
Using the Out-Of-Bag Model in the Cross-Validation Procedure
Pattern Recognition and Image Analysis. 2024. V.34. N4. P.1172-1176. DOI: 10.1134/S1054661824701232
Using the Out-Of-Bag Model in the Cross-Validation Procedure
Pattern Recognition and Image Analysis. 2024. V.34. N4. P.1172-1176. DOI: 10.1134/S1054661824701232
Даты:
Поступила в редакцию: | 20 апр. 2024 г. |
Принята к публикации: | 16 июл. 2024 г. |
Идентификаторы БД:
Нет идентификаторов
Цитирование в БД:
Пока нет цитирований