IPAB Workshop-11/11/2021

Title: An Overview of Meta-Learning: Introduction, Successes, and Challenges

Abstract: In this talk I will give an introduction and overview of the key ideas in meta-learning, and a taxonomy that can be used to easily understand the wide variety of techniques and applications in the field. I will highlight a range of interesting applications from within my group and beyond that show the diversity of use cases for meta-learning such as dealing with domain-shift, data augmentation, learning with label noise, and accelerating RL. Finally, I will discuss some outstanding underpinning research challenges, and application areas where  meta-learning may yet be productively applied.