Dipl.-Ing. Dr. Robert Peharz, Medical University, Graz

                               V O R T R A G

Oesterreichisches Forschungsinstitut fuer Artificial Intelligence(OFAI) der OSGK
Freyung 6/6, A-1010 Wien
Tel: +43-1-5336112-17,  Fax: +43-1-5336112-77, Email: sec@ofai.at

Dipl.-Ing. Dr. Robert Peharz
Medical University of Graz
Institute of Physiology / Interdisciplinary Developmental Neuroscience


Sum-Product networks (SPNs) are a new avenue for probabilistic
modeling. Using a deep network structure, they are able to represent
highly complex variable dependencies, while at the same time many
inference scenarios can be solved with computational costs linear in
the representation size of the SPN.
In this talk, an overview of SPNs is given, following their evolution
in literature. First we define SPNs for discrete random variables and
introduce the notions of completeness, consistency, decomposability and
network polynomials. Then we generalize SPNs to continuous random
variables and present some recent theoretical insights, in order to
draw a clearer picture of representational properties of SPNs. We
further discuss tractable inference mechanisms in SPNs, including
marginalization, the so-called differential approach to inference and
most-probable-explanation. Finally, an overview of existing learning
algorithms is given and results of SPNs applied to computer vision and
speech modeling are presented.


Time: Friday, 30th October 2015, 3:00 p.m. sharp

Location:  Oesterreichisches Forschungsinstitut
fuer Artificial Intelligence, OFAI
Freyung 6, Stiege 6, 1010 Wien


Univ.-Prof. Ing. Dr. Robert Trappl