Modulcode:	Inf-PatRec
Englische Bezeichnung:	Pattern Recognition
Modulverantwortliche(r):	Prof. Dr. Hauke Schramm
Turnus:	jedes Jahr im WS (WS14/15 WS15/16 WS16/17 WS17/18 WS18/19 WS19/20 WS20/21 WS21/22 WS22/23 WS23/24 WS24/25)
Präsenzzeiten:	2V 2Ü
ECTS:	6
Workload:	30 h lectures, 30 h exercises, 120 h self studies
Dauer:	ein Semester
Modulkategorien:	BSc-Inf-WP (BSc Inf (21)) WI (BSc Inf (15)) MSc-Inf-WP (MSc Inf (21)) 2F-MEd-Inf-WP (MEd-Hdl Inf (21)) 2F-MA-Inf-WP (2F-MA Inf (21)) MSc-WInf-WP-Inf (MSc WInf (21)) WI (MSc Inf (15)) EcoQuantFin (Export) WI (MEd Inf) WPI (MEd Inf) IG (MSc Inf) IS (MSc Inf)
Lehrsprache:	Englisch
Voraussetzungen:

Kurzfassung:

The field of Pattern Recognition deals with the problem of classifying complex data into pre-specified categories to enable automatic decisions. Most state-of-the-art classification frameworks utilize large amounts of data to develop robust statistical representations of the considered patterns and enhance class discrimination by sophisticated learning algorithms. This course explains the theoretical and practical aspects of fundamental pattern recognition techniques and enables the independent development and enhancement of classification systems.

Lernziele:

On completion of this module students will have knowledge of required statistical methods and important basic concepts of pattern classification techniques. They are able to (1) identify a suitable approach for a particular pattern recognition task, (2) design and implement a practical realization, and (3) evaluate its classification performance.

Lehrinhalte:

1. Basics of probability calculus
   Random variables, marginal distribution, conditional probability, Bayes rule, multivariate normal density, ...
2. Bayesian decision theory
   Discriminant functions, Bayes theorem, Bayes risk, decision boundaries
3. Maximum-likelihood parameter estimation
   Theory and practical applications
4. Non-parametric techniques
   Parzen windows, nearest neighbor classification

Weitere Voraussetzungen:

Mathematical basics of algebra and analysis.

Prüfungsleistung:

Written exam at the end of the course.

Lehr- und Lernmethoden:

Beamer presentation and use of software tools.

Verwendbarkeit:

Literatur:

R. Duda et al., "Pattern classification", Wiley, 2001

C. M. Bishop, "Pattern recognition and Machine learning", Springer, 2006

Verweise:

Kommentar:

Students are encouraged to bring their own laptops to the laboratory exercises and install latest version of Matlab or Octave with packages "statistics" and "image" from www.gnu.org/software/octave/.