700.370 (16S) Seminar on Data mining and Pattern Recognition in Intelligent Vehicle Technologies

Sommersemester 2016

Anmeldefrist abgelaufen.
... keine weiteren Termine bekannt

Überblick

Lehrende/r
LV-Titel englisch
Seminar on Data mining and Pattern Recognition in Intelligent Vehicle Technologies
LV-Art
Seminar (prüfungsimmanente LV )
Semesterstunde/n
2.0
ECTS-Anrechungspunkte
4.0
Anmeldungen
11 (20 max.) Anzahl der tatsächlich angemeldeten Studierenden
Organisationseinheit
Unterrichtssprache
Englisch
LV-Beginn
08.03.2016
eLearning
zum Moodle-Kurs

Zeit und Ort

Tag von - bis Raum Details
Mo, 14.03.2016 10:00 - 12:00 L4.1.02 ICT-Lab wöchentlich
Mo, 04.04.2016 10:00 - 12:00 L4.1.02 ICT-Lab wöchentlich
Mo, 11.04.2016 10:00 - 12:00 L4.1.02 ICT-Lab wöchentlich
Mo, 18.04.2016 10:00 - 12:00 L4.1.02 ICT-Lab wöchentlich
Mo, 25.04.2016 10:00 - 12:00 L4.1.02 ICT-Lab wöchentlich
Mo, 02.05.2016 10:00 - 12:00 L4.1.02 ICT-Lab wöchentlich
Mo, 09.05.2016 10:00 - 12:00 L4.1.02 ICT-Lab wöchentlich
Mo, 23.05.2016 10:00 - 12:00 L4.1.02 ICT-Lab wöchentlich
Mo, 30.05.2016 10:00 - 12:00 L4.1.02 ICT-Lab wöchentlich
Mo, 06.06.2016 10:00 - 12:00 L4.1.02 ICT-Lab wöchentlich
Mo, 13.06.2016 10:00 - 12:00 L4.1.02 ICT-Lab wöchentlich
Mo, 20.06.2016 10:00 - 12:00 L4.1.02 ICT-Lab wöchentlich
Mo, 27.06.2016 10:00 - 12:00 L4.1.02 ICT-Lab wöchentlich

LV-Beschreibung

Inhalt/e

The seminar has two major parts. In part one, we deal with various aspects of pattern recognition for INTELLIGENT VEHICLES TECHNOLOGIES and ROBOTICS. This part is based on different lectures that will be held during the semster. In part two, the students should choose a research paper and try to write a report and make a presentation about it. The overall structure of part two is: # A list of topics will be suggested and placed in Moodle. # To each topic 1 or 2 basic papers will be suggested, which contains basic related information (will be placed in Moodle) # A student selects a topic (groups of 2 students are allowed) # For each topic, 12 to 15 slides will be prepared by the students. # Dates for Mini seminar presentations: in the last 2 weeks of the semester will be announced.

Themen

  • * Introduction & Organisation
  • * Feature Selection ( Outlier Removal, Data Normalization , Missing data, Uncertainty Handling )
  • * Feature Generation ( Principal components analysis , Kernel Principal compon
  • * Clustering (Expectation Maximization, Nearest Neighbor, k-means , Self-organized maps)
  • * Supervised Learning (Perceptron, Perceptron learning algorithm, Multi-layered neural networks, back propagation, Linear Models, Nonlinear Models)
  • * Context Dependent Classification (Hidden Markov Models, Bayes Classifier)
  • * Model Evaluation
  • * Deep Learning (Convolutional Neural Network, Deep Belief Network, Auto encoder, Sparse Encoder, Boltzmann Machine)
  • * Introduction to Advanced Driver assistance Systems (ADAS)
  • * Applications in Image processing / machine Vision
  • * Introduction to ROBOTICS

Lehrziel

* Advanced analysis skills and complex problem solving (Big Data) * Object detection and recognition * Advanced applications of artificial intelligence (audio/video patterns recognition)

Literatur

Based on the books: * Pattern Recognition - Sergios Theodoridis * Data Mining: Practical Machine Learning Tools and Techniques - Ian H. Witten, Eibe Frank

Inhalt/e

The seminar has two major parts. In part one, we deal with various aspects of pattern recognition for INTELLIGENT VEHICLES TECHNOLOGIES and ROBOTICS. This part is based on different lectures that will be held during the semster. In part two, the students should choose a research paper and try to write a report and make a presentation about it. The overall structure of part two is: # A list of topics will be suggested and placed in Moodle. # To each topic 1 or 2 basic papers will be suggested, which contains basic related information (will be placed in Moodle) # A student selects a topic (groups of 2 students are allowed) # For each topic, 12 to 15 slides will be prepared by the students. # Dates for Mini seminar presentations: in the last 2 weeks of the semester will be announced.

Themen

  • * Introduction & Organisation
  • * Feature Selection ( Outlier Removal, Data Normalization , Missing data, Uncertainty Handling )
  • * Feature Generation ( Principal components analysis , Kernel Principal compon
  • * Clustering (Expectation Maximization, Nearest Neighbor, k-means , Self-organized maps)
  • * Supervised Learning (Perceptron, Perceptron learning algorithm, Multi-layered neural networks, back propagation, Linear Models, Nonlinear Models)
  • * Context Dependent Classification (Hidden Markov Models, Bayes Classifier)
  • * Model Evaluation
  • * Deep Learning (Convolutional Neural Network, Deep Belief Network, Auto encoder, Sparse Encoder, Boltzmann Machine)
  • * Introduction to Advanced Driver assistance Systems (ADAS)
  • * Applications in Image processing / machine Vision
  • * Introduction to ROBOTICS

Lehrziel

* Advanced analysis skills and complex problem solving (Big Data) * Object detection and recognition * Advanced applications of artificial intelligence (audio/video patterns recognition)

Literatur

Based on the books: * Pattern Recognition - Sergios Theodoridis * Data Mining: Practical Machine Learning Tools and Techniques - Ian H. Witten, Eibe Frank

Prüfungsinformationen

Beurteilungskriterien/-maßstäbe

Presentation + Report

Beurteilungskriterien/-maßstäbe

Presentation + Report

Beurteilungsschema

Note/Grade Benotungsschema

Position im Curriculum

  • Masterstudium Information and Communications Engineering (ICE) (SKZ: 488, Version: 15W.1)
    • Fach: Technical Complements (NC, ASR)
      • Wahl aus dem LV-Katalog (Anhang 5) ( 0.0h VK, VO, KU / 12.0 ECTS)
        • 700.370 Seminar on Data mining and Pattern Recognition in Intelligent Vehicle Technologies (2.0h SE / 4.0 ECTS)
  • Masterstudium Information and Communications Engineering (ICE) (SKZ: 488, Version: 15W.1)
    • Fach: Technical Complements (NC, ASR)
      • Wahl aus dem LV-Katalog (Anhang 5) ( 0.0h VK, VO, KU / 12.0 ECTS)
        • 700.370 Seminar on Data mining and Pattern Recognition in Intelligent Vehicle Technologies (2.0h SE / 4.0 ECTS)
  • Bachelorstudium Informationstechnik (SKZ: 289, Version: 12W.2)
    • Fach: Bachelorarbeit, Studienzweig Ingenieurwissenschaften
      • Seminar aus dem Bereich Ingenieurwissenschaften ( 2.0h SE / 3.0 ECTS)
        • 700.370 Seminar on Data mining and Pattern Recognition in Intelligent Vehicle Technologies (2.0h SE / 3.0 ECTS)
          Absolvierung im 6. Semester empfohlen
  • Bachelorstudium Informationstechnik (SKZ: 289, Version: 09W.2)
    • Fach: Bachelorarbeit und Seminar (Pflichtfach)
      • Seminar (zur Bachelorarbeit) ( 2.0h SE / 3.0 ECTS)
        • 700.370 Seminar on Data mining and Pattern Recognition in Intelligent Vehicle Technologies (2.0h SE / 3.0 ECTS)
  • Bachelorstudium Informationstechnik (SKZ: 289, Version: 06W.1)
    • Fach: Informationstechnische Vertiefung (Wahlfach)
      • Seminar ( 2.0h SE / 4.0 ECTS)
        • 700.370 Seminar on Data mining and Pattern Recognition in Intelligent Vehicle Technologies (2.0h SE / 4.0 ECTS)
  • Masterstudium Information Technology (SKZ: 489, Version: 06W.3)
    • Fach: Technischer Schwerpunkt (Intelligent Transportation Systems) (Pflichtfach)
      • 1.1-1.3 Vorlesung mit Kurs oder Vorlesung mit Seminar ( 6.0h VK/VS / 12.0 ECTS)
        • 700.370 Seminar on Data mining and Pattern Recognition in Intelligent Vehicle Technologies (2.0h SE / 4.0 ECTS)
  • Masterstudium Information Technology (SKZ: 489, Version: 06W.3)
    • Fach: Technische Ergänzung I (Pflichtfach)
      • 2.3 Vorlesung mit Kurs oder Seminar ( 2.0h VK/SE / 4.0 ECTS)
        • 700.370 Seminar on Data mining and Pattern Recognition in Intelligent Vehicle Technologies (2.0h SE / 4.0 ECTS)
  • Masterstudium Information Technology (SKZ: 489, Version: 06W.3)
    • Fach: Technische Ergänzung II (Pflichtfach)
      • 3.1-3.3 Vorlesung mit Kurs oder Vorlesung mit Seminar ( 6.0h VK/VS / 12.0 ECTS)
        • 700.370 Seminar on Data mining and Pattern Recognition in Intelligent Vehicle Technologies (2.0h SE / 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)
        • 700.370 Seminar on Data mining and Pattern Recognition in Intelligent Vehicle Technologies (2.0h SE / 4.0 ECTS)
  • Masterstudium Information Technology (SKZ: 489, Version: 06W.3)
    • Fach: Technischer Schwerpunkt (Media Engineering) (Pflichtfach)
      • 1.1-1.3 Vorlesung mit Kurs oder Vorlesung mit Seminar ( 6.0h VK/VS / 12.0 ECTS)
        • 700.370 Seminar on Data mining and Pattern Recognition in Intelligent Vehicle Technologies (2.0h SE / 4.0 ECTS)

Gleichwertige Lehrveranstaltungen im Sinne der Prüfungsantrittszählung

Sommersemester 2017
  • 700.370 SE Seminar on Data mining and Pattern Recognition in Intelligent Vehicle Technologies (2.0h / 4.0ECTS)
Sommersemester 2015
  • 700.370 SE Seminar on Data mining and Pattern Recognition in Intelligent Vehicle Technologies (2.0h / 4.0ECTS)
Sommersemester 2014
  • 700.370 SE Seminar on Data mining and Pattern Recognition in Intelligent Vehicle Technologies (2.0h / 4.0ECTS)
Sommersemester 2013
  • 700.370 SE Seminar on Pattern Recognition in Intelligent Vehicle Technologies (2.0h / 4.0ECTS)