Meta-Learning or "Learning To Learn"
Add to your list(s)
Download to your calendar using vCal
If you have a question about this talk, please contact Robert Pinsler.
This tutorial talk will introduce the concepts behind meta-learning or “Learning to Learn” with a focus on few-shot learning scenarios. Key meta-learning approaches including Model Agnostic Meta-Learning (MAML) and Prototypical Networks will be covered in detail. We’ll finish up by describing meta-learning applications such as few-shot image classification, view reconstruction, and meta-reinforcement learning.
This talk is part of the Machine Learning Reading Group @ CUED series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
|