Meta-Learning of Structured Task Distributions in Humans and Machines
international conference on learning representations, 2021.
Weibo:
Abstract:
In recent years, meta-learning, in which a model is trained on a family of tasks (i.e. a task distribution), has emerged as an approach to training neural networks to perform tasks that were previously assumed to require structured representations, making strides toward closing the gap between humans and machines. However, we argue that e...More
Tags
Comments