Pattern Recognition and Clustering

Code:

M475

Acronym:

M475

Keywords
Classification	Keyword
OFICIAL	Mathematics

Instance: 2010/2011 - 1S

Active?	Yes
Responsible unit:	Department of Mathematics
Course/CS Responsible:	Master in Mathematical Engineering

Cycles of Study/Courses

Acronym	No. of Students	Study Plan	Curricular Years	Credits UCN	Credits ECTS	Contact hours	Total Time
L:AST	0	Plano de Estudos a partir de 2008	3	-	7,5	-	202,5
L:CC	0	Plano de estudos de 2008 até 2013/14	3	-	7,5	-	202,5
L:F	0	Plano de estudos a partir de 2008	3	-	7,5	-	202,5
L:M	0	Plano de estudos a partir de 2009	3	-	7,5	-	202,5
M:EG	0	PE do Mestrado em Engenharia Geográfica	1	-	7,5	-	202,5
M:ENM	0	PE do Mestrado em Engenharia Matemática	1	-	7,5	-	202,5
			2
M:M	1	PE do Mestrado em Matemática	1	-	7,5	-	202,5
			2
M:MAO	1	PE Mestrado em MAOPI	1	-	7,5	-	202,5
M:SIG	0	PE do Mestrado em Sistemas de Informação Geográfic	1	-	7,5	-	202,5

Teaching language

Portuguese

Objectives

Introduce the basic concepts of statistical pattern recognition and cluster analysis. It is also intended that the student is able to apply the concepts learned in real and simulated problems.

Program

Introduction and formulation of a pattern recognition recognition problem; some application examples. Random vectors and their properties: probability distributions, parameter estimation, linear transformations, principal components. Statistical decision theory. Parametric methods of discriminant analysis: Gaussian models. Nonparametric methods of discriminant analysis: Kernel methods and K-NN. Neural Networks, Decision and Regression Trees, Support Vector Machines. Unsupervised classification: hierarchical and nonhierarchical clustering.

Mandatory literature

000040415. ISBN: 0-471-05669-3
000040365. ISBN: 0-387-95284-5
000039952. ISBN: 0-521-46086-7

Teaching methods and learning activities

The lessons are accompanied by materials provided by the teacher, including exercise sheets for each of the sections programmatic, and also the use of statistical software.

Software

Software R

Evaluation Type

Distributed evaluation with final exam

Assessment Components

Description	Type	Time (hours)	Weight (%)	End date
Attendance (estimated)	Participação presencial	70,00
	Total:	-	0,00

Calculation formula of final grade

Final exam and projects. To be approved, the student must have a positive score both on the final exam and projects. The exam has a weight of 50% and the computational projects also 50%.