|
ИСТИНА |
Войти в систему Регистрация |
ФНКЦ РР |
||
Learning to Generate Synthetic Training Data Using Gradient Matching and Implicit Differentiationстатья
- Авторы: Medvedev Dmitry, Alexander D’yakonov
- Сборник: Communications in Computer and Information Science
- Серия: Recent Trends in Analysis of Images, Social Networks and Texts. AIST 2021
- Том: 1573
- Год издания: 2022
- Издательство: Springer International Publishing
- Местоположение издательства: New York
- Первая страница: 138
- Последняя страница: 150
- DOI: 10.1007/978-3-031-15168-2_12
- Аннотация: Using huge training datasets can be costly and inconvenient. This article explores various data distillation techniques that can reduce the amount of data required to successfully train deep networks. Inspired by recent ideas, we suggest new data distillation techniques based on generative teaching networks, gradient matching, and the Implicit Function Theorem. Experiments with the MNIST image classification problem show that the new methods are computationally more efficient than previous ones and allow to increase the performance of models trained on distilled data.
- Добавил в систему: Дьяконов Александр Геннадьевич