Few-shot Learning with Meta-Learning: Progress Made and Challenges Ahead
MetadataShow full item record
A lot of the recent progress on many AI tasks enabled in part by the availability of large quantities of labeled data. Yet, humans are able to learn concepts from as little as a handful of examples. Meta-learning is a very promising framework for addressing the problem of generalizing from small amounts of data, known as few-shot learning. In meta-learning, our model is itself a learning algorithm: it takes input as a training set and outputs a classifier. For few-shot learning, it is (meta-)trained directly to produce classifiers with good generalization performance for problems with very little labeled data. In this talk, I'll present an overview of the recent research that has made exciting progress on this topic (including my own) and will discuss the challenges as well as research opportunities that remain.
Showing items related by title, author, creator and subject.
The effects of time on employment selection test performance : learning disabled versus non-learning disabled Collins, William C. (Georgia Institute of Technology, 1994-05)
Cox, Michael Thomas (Georgia Institute of Technology, 1996-05)
Learning to troubleshoot: Multistrategy learning of diagnostic knowledge for a real-word problem solving task Ram, Ashwin; Narayanan, Sundaram; Cox, Michael Thomas (Georgia Institute of Technology, 1993)This article presents a computational model of the learning of diagnostic knowledge based on observations of human operators engaged in a real-world troubleshooting task. We present a model of problem solving and ...