Probabilistic Programming: Machine Learning for the Masses?
Joost-Pieter Katoen (RWTH Aachen) gives a historical perspective and indicates what formal methods can mean for probabilistic programs.
TU Wien, Campus Gußhaus
1040 Vienna, Gußhausstraße 27-29
Stiege 1, 6. Stock, CD0603
Probabilistic programs describe recipes on how to infer conclusions about big data from a mixture of uncertain data and real-world observations. Bayesian networks, a key model in decision making, are simple instances of such programs. Probabilistic programs steer autonomous robots and self-driving cars, are key to describe security mechanisms, naturally encode randomised algorithms, and are rapidly encroaching AI and machine learning.
About Joost-Pieter Katoen
Joost-Pieter Katoen is a full professor at RWTH Aachen University in the Software Modeling and Verification (MOVES) group and part-time associated to the Formal Methods & Tools group at the University of Twente. Since 2013, he holds a distinguished professorship at RWTH Aachen University and is a member of the Academia Europaea.