Universiteit Leiden

nl en

Lecture

Florence Nightingale Colloquium presents Joaquin Vanschoren

Date
Friday 22 January 2021
Time
Explanation
The seminar is targeted at a broad audience, in particular we invite master students, PhD candidates and supervisors interested or involved in the Data Science Research programme as well as colleagues from LIACS and MI to attend. The seminar is organized by the DSO, MI and LIACS.
Serie
Florence Nightingale Colloquium
Address
Kaltura Live Room
Joaquin Vanschoren is Assistent Professor at the Eindhoven University of Technology

Learning how to learn how to learn

Machine learning knows many useful applications, yet requires significant experience on how to design and train accurate and robust models. Automated machine learning (AutoML) helps democratize AI by automating the search for the best models. Perhaps ironically, most such AutoML systems start from scratch with every new given task. In this talk, we show how we can learn how to design machine learning models from experience with many prior tasks. Much like human machine learning experts, such systems will get better with every new task they are given and every model they have tried. In this way, they would never stop learning and be better equipped to help us build better machine learning models for increasingly difficult challenges.

Join the webinar via Kaltura Live Room

Kaltura Live Room works best in Edge, Chorme and Firefox. Make sure you activate your camera and microphone beforehand in order to interact with the speaker and participate in discussion. The room opens for the public at 12:50.

Register for the Kaltura Live Room link
This website uses cookies.  More information.