700.395 (17W) Data Mining and Neurocomputing

Wintersemester 2017/18

Anmeldefrist abgelaufen.

Erster Termin der LV
20.11.2017 13:30 - 20:00 , HS 11
... keine weiteren Termine bekannt

Überblick

Lehrende/r
LV-Titel englisch
Data Mining and Neurocomputing
LV-Art
Vorlesung-Kurs (prüfungsimmanente LV )
Semesterstunde/n
2.0
ECTS-Anrechungspunkte
4.0
Anmeldungen
23 (25 max.)
Organisationseinheit
Unterrichtssprache
Englisch
mögliche Sprache/n der Leistungserbringung
Deutsch , Englisch
LV-Beginn
01.11.2017
eLearning
zum Moodle-Kurs
Seniorstudium Liberale
Ja

LV-Beschreibung

Intendierte Lernergebnisse

The students

  • are able use the basic methods for datamining and neurocomputing (Deep Learning),
  • have a good command of  datamining approaches for different applications
  • are able to transfer the acquired knowledge to solve complex machine learning  applications for industry and research,
  • are able to describe the state-of-the-art of the presented topics

Lehrmethodik

The course has two major parts. The first part consists of the theoretical and methodic fundamentals that will be introduced during the lecture. The second part consists of intensive lab work where students can implement, test, and apply the presented methods. The major lab language will be python using TensorFlow and Scikit-Learn libraries. 

Inhalt/e

The course focuses  on data selection, cleaning and preparation. Then, it covers  the topics of dimension reduction, for example using principle components analysis and Auto-encoders. Additionally, different types of linear and non-linear models will be discussed in details with focus on neural models. Finally, different evaluation metrics and performance analysis s will be presented.

  • Mathematical basics                                                            
  • Data selection and preparation                                                            
  • Bayesian models                                                            
  • Linear models                                                            
  • Non linear models                                                            
  • Artificial Neural Networks
  • Feedforward Neural Networks
  • Backpropagation
  • Recurrent Neural Networks                                                            
  • Deep Learning                                                            
  • Evaluation Metrics      

Erwartete Vorkenntnisse

Basic knowledge of any programming language

Literatur

Data Mining: Practical Machine Learning Tools and Techniques# Publisher: Morgan Kaufmann; 2 edition (June 22, 2005)# Ian H. Witten, Eibe Frank# Language: English# ISBN-10: 0120884070# ISBN-13: 978-0120884070

Principles of Neuro Computing for Science & Engineering# Fredric M. Ham# Ivica Kostanic# ISBN: 0-07-025966-6# Publisher: McGraw-HillGeorge Papadourakis, “Introduction to Neural Networks”, Lecture Notes

Prüfungsinformationen

Prüfungsmethode/n

Written Exam + Project 

Prüfungsinhalt/e

The student should pass a written exam successfully which reflects the understanding of the presented concepts and approaches. Additionally, the students should design and implement a fully working system in the field of machine learning.

Beurteilungskriterien/-maßstäbe

The final evaluation is divided as follows:

70% Exam

30% Project


Beurteilungsschema

Note/Grade Benotungsschema

Position im Curriculum

  • Masterstudium Information and Communications Engineering (ICE) (SKZ: 488, Version: 15W.1)
    • Fach: Information and Communications Engineering: Supplements (NC, ASR) (Wahlfach)
      • Wahl aus dem LV-Katalog (Anhang 4) ( 0.0h VK, VO, KU / 14.0 ECTS)
        • 700.395 Data Mining and Neurocomputing (2.0h VC / 4.0 ECTS)
  • Masterstudium Information and Communications Engineering (ICE) (SKZ: 488, Version: 15W.1)
    • Fach: Technical Complements (NC, ASR) (Wahlfach)
      • Wahl aus dem LV-Katalog (Anhang 5) ( 0.0h VK, VO, KU / 12.0 ECTS)
        • 700.395 Data Mining and Neurocomputing (2.0h VC / 4.0 ECTS)
  • Masterstudium Information and Communications Engineering (ICE) (SKZ: 488, Version: 15W.1)
    • Fach: Information and Communications Engineering: Supplements (NC, ASR) (Wahlfach)
      • Wahl aus dem LV-Katalog (Anhang 4) ( 0.0h VK, VO, KU / 14.0 ECTS)
        • 700.395 Data Mining and Neurocomputing (2.0h VC / 4.0 ECTS)
  • Masterstudium Information and Communications Engineering (ICE) (SKZ: 488, Version: 15W.1)
    • Fach: Technical Complements (NC, ASR) (Wahlfach)
      • Wahl aus dem LV-Katalog (Anhang 5) ( 0.0h VK, VO, KU / 12.0 ECTS)
        • 700.395 Data Mining and Neurocomputing (2.0h VC / 4.0 ECTS)
  • Masterstudium Information and Communications Engineering (ICE) (SKZ: 488, Version: 15W.1)
    • Fach: Autonomous Systems and Robotics: Advanced (ASR) (Wahlfach)
      • Wahl aus dem LV-Katalog (siehe Anhang 3) ( 0.0h VK, VO / 30.0 ECTS)
        • 700.395 Data Mining and Neurocomputing (2.0h VC / 4.0 ECTS)
  • Masterstudium Information and Communications Engineering (ICE) (SKZ: 488, Version: 15W.1)
    • Fach: Autonomous Systems and Robotics (WI) (Wahlfach)
      • Wahl aus dem LV-Katalog (siehe Anhang 3) ( 0.0h VK, VO / 30.0 ECTS)
        • 700.395 Data Mining and Neurocomputing (2.0h VC / 4.0 ECTS)
  • Masterstudium Information Technology (SKZ: 489, Version: 06W.3)
    • Fach: Research Track (Methodischer Schwerpunkt) (Pflichtfach)
      • 4.2'-4.3' Theoretisch-Methodische Lehrveranstaltung I/II ( 0.0h VO/VK/VS/KU/PS / 6.0 ECTS)
        • 700.395 Data Mining and Neurocomputing (2.0h VC / 4.0 ECTS)

Gleichwertige Lehrveranstaltungen im Sinne der Prüfungsantrittszählung

Sommersemester 2019
  • 700.395 VC Data Mining and Neurocomputing (2.0h / 4.0ECTS)
Wintersemester 2016/17
  • 700.395 VC Data Mining and Neurocomputing (2.0h / 4.0ECTS)
Wintersemester 2015/16
  • 700.395 VC Data Mining and Neurocomputing (2.0h / 4.0ECTS)
Wintersemester 2013/14
  • 700.395 VK Data Mining in Intelligent Transportation and Logistics (2.0h / 4.0ECTS)
Wintersemester 2012/13
  • 700.395 VK Data Mining in Intelligent Transportation and Logistics (2.0h / 4.0ECTS)