Direkt zum Inhalt springen
Computer Vision Group
TUM Department of Informatics
Technical University of Munich

Technical University of Munich

Home Teaching Summer Semester 2016 Probabilistic Graphical Models in Computer Vision (IN2329) (2h + 2h, 5 ECTS)


This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
teaching:ss2016:lecture_graphical_models [2016/06/22 10:15]
Csaba Domokos
teaching:ss2016:lecture_graphical_models [2016/07/18 11:03] (current)
Csaba Domokos
Line 10: Line 10:
 Directed and undirected graphical models Directed and undirected graphical models
-  * Bayesian ​Network +  * Bayesian ​network 
-  * Markov ​Random Field +  * Markov ​random field 
-  * Conditional ​Random Field+  * Conditional ​random field
 Parameter learning for MRF and CRF models Parameter learning for MRF and CRF models
   * Gradient based optimization   * Gradient based optimization
   * Stochastic gradient descent   * Stochastic gradient descent
-  * Structured ​Support Vector Machines+  * Structured ​support vector machine
 Exact MAP inference methods for MRFs Exact MAP inference methods for MRFs
-  * Belief propagation on trees: ​max-sum algorithm+  * Belief propagation on trees: ​Max-sum algorithm
   * Binary graph cuts   * Binary graph cuts
   * Branch-and-mincut   * Branch-and-mincut

Rechte Seite

Informatik IX
Chair for Computer Vision & Artificial Intelligence

Boltzmannstrasse 3
85748 Garching