Course

MLWR - Machine Learning and Scientific Computing

PDF Course Catalog Deutsche Version: MLWR

Version: 1 | Last Change: 27.09.2019 16:03 | Draft: 0 | Status: vom verantwortlichen Dozent freigegeben

Long name Machine Learning and Scientific Computing
Approving CModule MLWR_MaCSN, MLWR_MaET, MLWR_MaTIN
Responsible
Prof. Dr. Beate Rhein
Professor Fakultät IME
Level Master
Semester in the year summer semester
Duration Semester
Hours in self-study 60
ECTS 5
Professors
Prof. Dr. Beate Rhein
Professor Fakultät IME
Requirements Basic knowledge of probability theory and machine learning
Language German
Separate final exam Yes
Literature
keine/none
Final exam
Details
Questions of different degrees of difficulty and different aspects of the course (course of a project, performance measures, data protection, etc.)
some in-depth questions
It is possible to write down sketches and formulas.
Minimum standard
be able to describe the rough sequence of a machine learning or scientific computing project
Being able to explain discussed procedures roughly
Exam Type
Questions of different degrees of difficulty and different aspects of the course (course of a project, performance measures, data protection, etc.)
some in-depth questions
It is possible to write down sketches and formulas.

Learning goals
Knowledge
Approximation methods
metamodeling
regression

Multi-criteria optimization
formulation
Pareto front
algorithms
visualization

Advanced Cluster Analysis

Association Pattern Mining

Outlier Detection

Advanced classification procedures

possibly text recognition, web mining, time series analysis
Skills
Be familiar with mathematical methods, which are suitable for application tasks,
convert them into run-time and memory optimized programs using numerical methods and skilful implementation
Know approximation methods and select and apply the appropriate method for a task
Formulate an application task as a multi-criteria optimization task and solve it in a program
Know methods of machine learning, select and apply appropriate procedures
Expenditure classroom teaching
Type Attendance (h/Wk.)
Lecture 2
Exercises (whole course) 2
Exercises (shared course) 0
Tutorial (voluntary) 0
Special literature
Data Mining - The Textbook, C.C. Aggarwal, Springer Verlag, ISBN 978-3-319-14141-1
Strukturoptimierung, L. Harzheim, Harri Deutsch Verlag, ISBN 978-3-8085-5659-7
Special requirements
-
Accompanying material
Lecture slides (electronic)
possibly tutorials, instructional videos or links to them
Practical task, partly with data sets and literature
Separate exam
none

Learning goals
Skills
Apply and program methods of approximation, multicriteria optimization or machine learning
efficiently implement numerical methods
Evaluate the complexity of algorithms
Expenditure classroom teaching
Type Attendance (h/Wk.)
Practical training 1
Tutorial (voluntary) 0
Special literature
keine/none
Special requirements
-
Accompanying material
Electronic task description
sample programs
Electronic tutorials for self-study
Separate exam
none

Impressum
Datenschutzhinweis
Haftungshinweis
Bei Fehlern, bitte Mitteilung an die
Webredaktion der Fakultät IME

© 2022 Technische Hochschule Köln