Meta Learning recipe, black-box adaptation, optimization based approaches
Probabilistic formulation of meta-learning(recap)
General recipe of meta-learning algorithms
Black-box adaptation approaches
Optimization-based meta-learning
많이 사용하는 dataset으로는 Omniglot, Mini-Imagenet, CIFAR, CUB, CelebA 등이 있다.
Mechanistic view
Probabilistic view
General recipe - Meta learning algorithm을 design 하는 방법