13
Discrete Optimization for Vision and Learning

Discrete Optimization for Vision and Learning. Who? How? M. Pawan Kumar Associate Professor Ecole Centrale Paris Nikos Komodakis Associate Professor Ecole

Embed Size (px)

Citation preview

Discrete Optimization for Vision and Learning

Who? How?

M. Pawan KumarAssociate ProfessorEcole Centrale Paris

Nikos KomodakisAssociate Professor

Ecole des Ponts

7 lectures. 1 exam. All in English.

Where? When?

Starts on 16th January, 09h45 – 13h00

Why?

How can I change the scenery?

Why?

Where is my car?

car

roadgrass

treeskysky

Why?

Where are my arms? My legs?

What?

Input x

Output y

Energy of y

What?

Energy Minimization

Obtain output y with minimum energy

Learning

Obtain energy using training samples

Energy of y

Syllabus

• Dynamic Programming– e.g. Shortest paths, Belief propagation

• Submodularity– e.g. Max flow, Min cut

• Convex Relaxations– e.g. Linear and semidefinite programming

• Parameter Estimation– e.g. SVM, Maximum likelihood

Two equations (reparameterization) !!

Analysis

• Which algorithm is most efficient?

• Which algorithm is most accurate?

• What algorithm should I use?

• Offered in 2014 as an MVA course

• University of Crete, Greece

• Ecole Centrale Paris– http://cvn.ecp.fr/personnel/pawan

• Coursera– http://www.coursera.org/ecp

Previous Courses

Evaluation

• Programming assignments– Graph Cuts– LP Relaxation

• One written exam– Half “easy” questions– Half “difficult” theoretical questions– “Missing information in publications”

Questions?

• Look at our research and previous courses– Search ‘Nikos Komodakis’– Search ‘M. Pawan Kumar’

• Send us an email– [email protected][email protected]