BEGIN:VCALENDAR
VERSION:2.0
PRODID:https://github.com/derhansen/sf_event_mgt
METHOD:PUBLISH
BEGIN:VEVENT
UID:6158-2022@rg-bremen-oldenburg.gi.de
CLASS: PUBLIC
SUMMARY:Informatik Kolloquium: AutoML - From Full Automation to a Human-Cen
 tric Approach
DESCRIPTION:Speaker: Dr. Marius Lindauer\n\nAbstract\n\nTraining any machin
 e learning pipeline always comes with a multitude of different design decis
 ions, incl. hyperparameters, neural architectues, machine learning algorith
 ms, preprocessing, and even more.Choosing them manually can be tedious and 
 error-prone. Automated machine learning\n\n(AutoML) supports developers and
  researchers by proposing solutions to all these design decisions. Therefor
 e, AutoML canh elp find ML solutions with better predictive performance, fa
 ster inference time, smaller memory footprint, improved fairness, or smalle
 r CO2 footprint. Although automating the entire ML design might seem appeal
 ing and contribute to the democratization of AI, AutoML cannot be successfu
 l without any human being involved. In my talk, I will cover the main conce
 pts of AutoML and argue that a more human-centric approach is needed not on
 ly in AI but also in AutoML.\n\nShort Bio:\n\nProf. Dr. Marius Lindauer is 
 full professor of machine learning at Leibniz University Hannover. He recei
 ved his PhD from the University of Potsdam\n\n(Germany) in 2015 under Prof.
  Dr. Thorsten Schaub and Prof. Dr. Holger Hoos. From 2014 to 2019, he was P
 ostDoc and later junior research group lead at the University of Freiburg u
 nder Prof. Dr. Frank Hutter. Besides being a member of ELLIS, he is one of 
 the co-heads of automl.org and co-founder of the research network COSEAL, t
 he AutoML conference and the Institute of AI (LUH|AI) at the Leibniz Univer
 sity Hannover. He won several competitions, including SAT solving, ASP solv
 ing, and automated machine learning, and his open-source packages are downl
 oaded more than 70k times each month. He gave several tutorials at renowned
  AI conferences and summer schools, such as AAAI, IJCAI and ESSAI. In 2022,
  he was awarded an ERC starting grant, the most prestigious research grant 
 for European young researchers. His research interests include automated ma
 chine learning (AutoML), reinforcement learning, interpretable and sustaina
 ble AI.
LOCATION:Uni Bremen, Cartesium, Rotunde
DTSTAMP:20240115T091037Z
DTSTART:20240206T151500Z
DTEND:20240206T163000Z
END:VEVENT
END:VCALENDAR