Meta-learning methods optimize for the type of model they are intending to produce.
How meta-learning can be applied to incredibly diverse deep learning models? 🧵
How meta-learning can be applied to incredibly diverse deep learning models? 🧵
The goal of meta-learning is to train a model on a variety of learning tasks so that it can solve new tasks with very little training.
2/5
2/5
In ‘Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks’ @chelseabfinn, @pabbeel, and @svlevine introduced a meta-learning method that is both general and model-agnostic.
3/5
3/5
MAML can be applied to any algorithm that has been trained using a gradient descent procedure.
The paper inspired a new generation of research and implementations in the field of meta-learning.
4/5
The paper inspired a new generation of research and implementations in the field of meta-learning.
4/5
Loading suggestions...