University of Cambridge > Talks.cam > Machine Learning Journal Club > Efficient Bayesian Task-Level Transfer Learning

Efficient Bayesian Task-Level Transfer Learning

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

If you have a question about this talk, please contact Philip Sterne.

I propose to split this week’s reading group into two parts. For the first half I am thinking of showing a video of the first half of Josh Tenenbaum’s invited talk at ICML which introduces some of the basic ideas behind his recent research.

For the second half of the meeting I would like to briefly discuss a recent paper which uses a similar model as the one that Tenenbaum uses in cognitive science but for a practical application:

`Efficient Bayesian Task-Level Transfer Learning’ By Dan Roy and Leslie Kaebling. http://web.mit.edu/droy/www/papers/ijcai07-droy.pdf

Sorry again about the late notice. This is a short paper so not too much reading is needed in order to get the basic idea. We probably won’t have time to cover the technical details anyway.

This talk is part of the Machine Learning Journal Club series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2019 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity