AI Seminar: Deep Machines That Know When They Do Not Know

Thursday, December 5, 2019 4:00 pm - 4:00 pm EST (GMT -05:00)

Kristian Kersting
Computer Science Department
Centre for Cognitive Science
Technische Universität Darmstadt

Our minds make inferences that appear to go far beyond standard machine learning. Whereas people can learn richer representations and use them for a wider range of learning tasks, machine learning algorithms have been mainly employed in a stand-alone context, constructing a single function from a table of training examples. 

In this talk, I shall touch upon a view on machine learning, called probabilistic programming, that can help capture these human learning aspects by combining high-level programming languages and probabilistic machine learning — the high-level language helps reduce the cost of modelling and probabilities help quantifying when a machine does not know something. Since probabilistic inference remains intractable, existing approaches leverage deep learning for inference. Instead of “going down the full neural road,” I shall argue to use sum-product networks, a deep but tractable architecture for probability distributions. This can speed up inference in probabilistic programs, as I shall illustrate for unsupervised science understanding, and even pave the way towards automating density estimation, making machine learning accessible to a broader audience of non-experts.

This talk is based on joint works with many people such as Carsten Binnig, Zoubin Ghahramani, Andreas Koch, Alejandro Molina, Sriraam Natarajan, Robert Peharz, Constantin Rothkopf, Thomas Schneider, Patrick Schramwoski, Xiaoting Shao, Karl Stelzner, Martin Trapp, Isabel Valera, Antonio Vergari, and Fabrizio Ventola.

Light refreshments will be available.


Bio: Kristian Kersting is a full professor (W3) for AI and ML at TU Darmstadt. After receiving his Ph.D. from U. Freiburg in 2006, he was with MIT, Fraunhofer IAIS, U. Bonn, and TU Dortmund. His main research interests are (deep) probabilistic programming and learning. Kristian has published over 170 peer-reviewed articles.

He is an EurAI Fellow, an ELLIS Fellow and received the inaugural German AI Award (Deutscher KI-Preis) 2019, as well as several paper awards (TPM 2019, AIIDE 2015, ECML 2006) and the EurAI Dissertation Award 2006. Kristian has been on the (senior) PC of major AI/ML conferences (e.g., AAAI, ICML, IJCAI, NeurIPS, ICLR, and CVPR) and co-chaired the PC of ECML PKDD 2020, 2013, and UAI 2017. He is the EiC of Frontiers in ML and AI and a (former) AE of TPAMI, JAIR, AIJ, DAMI, and MLJ.