A Semi-Supervised Adversarial Robust Model-Agnostic Meta-Learning Method
The meta model developed by meta learning is expected to have the ability of "learning to learn". Therefore, it can quickly adapt to new tasks based on the learned "meta knowledge", with a small number of gradient descent steps to fine-tune the model using a few labeled training...
Сохранить в:
| Главный автор: | |
|---|---|
| Формат: | Artigo |
| Язык: | Inglês |
| Опубликовано: |
Editorial Office of Computer Engineering
2022-12-01
|
| Серии: | Jisuanji gongcheng |
| Предметы: | |
| Online-ссылка: | https://www.ecice06.com/fileup/1000-3428/PDF/20221214.pdf |
| Метки: |
Нет меток, Требуется 1-ая метка записи!
|