University of Cambridge > Talks.cam > Machine Learning @ CUED > Towards true end-to-end learning & optimization

  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

Towards true end-to-end learning & optimization

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

If you have a question about this talk, please contact Pat Wilson.

Deep neural networks automatically learn representations from raw data, but their architectures and hyperparameters still typically need to be defined manually by human experts. In this talk, I will discuss extensions of Bayesian optimization for effectively searching in this combined space of architectures and hyperparameters, thereby paving the way to fully automated machine learning (AutoML) with neural networks. I will first show competition-winning practical AutoML systems and then focus on speeding up AutoML (sometimes up to 100-fold) by reasoning over data subsets and partial learning curves. I will also briefly show related applications to the end-to-end optimization of algorithms for solving hard combinatorial problems and discuss recent progress on weight optimization by variants of stochastic gradient descent.

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

CCCRR Vascular Biology Research Seminars The Cambridge Trust for New Thinking in Economics ‘Geographies of Radical Difference’

Other talks

Finding meaning in English writing Scaling of tissue proportions to body size during vertebrate development Migration in Science Anglo-Ottoman encounter in the Age of the Beloveds Evolution’s Bite: Dental evidence for the diets of our distant ancestors Surrogate models in Bayesian Inverse Problems
 

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