University of Cambridge > Talks.cam > Machine Learning @ CUED > Learning Task Relations in Multi-Task Learning

  Browse A-Z

Log in

Cambridge users (raven)details Other usersdetails No account?details

Information on

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

Learning Task Relations in Multi-Task Learning

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Louise Segar.

Via Skype

In this talk, I present three of my works to learn task relations for multi-task learning. The first work is to learn pairwise relations for multiple tasks based on a task covariance. The second work learns a multi-task kNN classifier where the classification of each data point depends on data points from all the tasks. The third work models tasks in a hierarchical structure and aims to learn the hierarchical structure as well as the model parameters in a principled framework.

This talk is part of the Machine Learning @ CUED series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Meeting the Challenge of Healthy Ageing in the 21st Century Behavioural and Clincial Neuroscience Seminars Reading Group on Principles of Neural Design Quantum Matter Seminar Abcam meetings Bioinformatics jounal club for the -omics

Other talks

Propaganda porcelain: The mirror of the Russian revolution and its consequences Handbuchwissenschaft, or: how big books maintain knowledge in the twentieth-century life sciences Finding alternatives: when circumstances suddenly change Zone 6 Convention
 

© 2006-2024 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity