University of Cambridge > Talks.cam > Machine Learning Reading Group @ CUED > Learning to Learn

  Browse A-Z

Log in

Googledetails Microsoftdetails

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹ️ Information

Learning to Learn

Download to your calendar using vCal

If you have a question about this talk, please contact Alessandro Davide Ialongo .

Abstract

Learning to Learn methods, or Meta-Learning, involve replacing hand-crafted aspects of conventional learning algorithms with more flexible features that can be learnt from data. We introduce and review recent work on learning to learn in the contexts of optimisation and few-shot learning.

Recommended Reading

There is no particular recommended reading, but the following papers will be discussed among others:
  • “Learning to learn without gradient descent by gradient descent”, Chen et al., ICML 2017
  • “Matching Networks for One Shot Learning”, Vinyals et al., NIPS 2016

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.

Other lists

Cambridge University Engineering Department, Room LR10 Faculty of Education, Mary Allan Building,Boulind 8 & 9, Homerton College, Hills Road, Cambridge CB2 8PQ Institute of Metabolic Science (IMS), Level 4 ATC, Seminar rooms 1,2 & 3

Other talks

Talk TBC Talk title TBC Morning Tea and Coffee Teams Announced Group Work Title TBC
 

© 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity