Dobbelt professortiltrædelsesfore-læsning ved Christian Igel og Corinna Cortes – Københavns Universitet

Dobbelt professortiltrædelsesfore-læsning ved Christian Igel og Corinna Cortes

Første forelæsning er kl. 14.00. Anden forelæsning er kl. 15.15. Der er efterfølgende reception 

Kl. 14.00 Towards Autonomous Machine Learning
- tiltrædelsesforelæsning ved professor mso Christian Igel

Abstract 

Machine learning algorithms are already an integral part of today's scientific computing.  Despite their successes in various application domains, there are fundamental challenges that must be met if we are to develop more general learning systems. For example, present algorithms often lack autonomy in the sense that they require a human expert to tune the method and its parameters, to find an appropriate data representation, etc.

The talk starts with a short primer on supervised machine learning with a focus on the role of prior knowledge for proper generalization.  As a concrete example for increasing autonomy, semi-automatic model selection for support vector machines is considered. Applications are reviewed and links to biological learning systems are discussed.

Bio

Christian Igel studied Computer Science at the Technical University of Dortmund. He received his doctoral degree from the Faculty of Technology at Bielefeld University in 2002 and his habilitation from the Ruhr-University Bochum in 2010.  From 2002 to 2010 he was a junior professor for Optimization of Adaptive Systems at the Institut für Neuroinformatik, Ruhr-University Bochum. In October 2010 Christian joined DIKU as a professor with special duties in Machine Learning. His research concerns theory and application of statistical machine learning and biologically-inspired computing.

Kl. 15.15 Machine Learning - Modern Times
- tiltrædelsesforelæsning ved adjungeret professor Corinna Cortes

Abstract 

Today's large-scale data sets and streams present machine learning  with unprecedented challenges in keeping up with the deluge of records to be processed and scored. In this talk, I will discuss some of the algorithmic advances and implementation solutions we have designed at Google to effectively and efficiently handle these problems. The talk will discuss machine learning examples from a number of Google applications including Gmail, Image, and Product Search. 

Bio:

Corinna Cortes is the Head of Google Research, NY,

where she is working on a broad range of theoretical and applied large-scale
machine learning problems. Prior to Google, Corinna spent more than ten years at AT&T Labs - Research, formerly AT&T Bell Labs, where she held a distinguished research position.

Corinna's research work is well-known in particular for her contributions to the theoretical foundations of support vector machines (SVMs) for which she jointly with Vladimir Vapnik received the 2008 Paris Kanellakis Theory and Practice Award, and for her work on data-mining in very large data sets for which she was awarded the AT&T Science and Technology Medal in the year 2000.

Corinna received her MS degree in Physics from the Niels Bohr Institute in Copenhagen and joined AT&T Bell Labs as a researcher in 1989. She received her Ph.D. in computer science from the University of Rochester in 1993.

Corinna is also a competitive runner, placing third in the More Marathon in New York City in 2005, and a mother of two.