迁移学习

迁移学习Transfer Learning-入门|机器学习

定义 Transfer Learning: The ability of a system to recognize and apply knowledge and skills learned in previous tasks to novel tasks (or new domains) 问题类型 Data not directly related to the task considered Training and future (test) data follow the same distribution, and are in same feature space 应用场景 网络结构 迁移学习类别 Transfer Learning Settings Related Areas Source Domain Labels Target Domain Labels Tasks Inductive Transfer Learning Multi-task Learning Available Available Regression, Classification Self-taught Learning Una...