700.370 (15S) Seminar on Data mining and Pattern Recognition in Intelligent Vehicle Technologies

Sommersemester 2015

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
02.03.2015
eLearning
zum Moodle-Kurs

Zeit und Ort

Tag von - bis Raum Details
Mo, 02.03.2015 10:00 - 12:00 L4.1.01 wöchentlich
Mo, 09.03.2015 10:00 - 12:00 L4.1.01 wöchentlich
Mo, 16.03.2015 10:00 - 12:00 L4.1.01 wöchentlich
Mo, 23.03.2015 10:00 - 12:00 L4.1.01 wöchentlich
Mo, 13.04.2015 10:00 - 12:00 L4.1.01 wöchentlich
Mo, 20.04.2015 10:00 - 12:00 L4.1.01 wöchentlich
Mo, 27.04.2015 10:00 - 12:00 L4.1.01 wöchentlich
Mo, 04.05.2015 10:00 - 12:00 L4.1.01 wöchentlich
Mo, 11.05.2015 10:00 - 12:00 L4.1.01 wöchentlich
Mo, 18.05.2015 10:00 - 12:00 L4.1.01 wöchentlich
Mo, 01.06.2015 10:00 - 12:00 L4.1.01 wöchentlich
Mo, 08.06.2015 10:00 - 12:00 L4.1.01 wöchentlich
Mo, 15.06.2015 10:00 - 12:00 L4.1.01 wöchentlich
Mo, 22.06.2015 10:00 - 12:00 L4.1.01 wöchentlich
Mo, 29.06.2015 10:00 - 12:00 L4.1.01 wöchentlich

LV-Beschreibung

Inhalt/e

In the lecture we deal with various aspects of pattern recognition and their applications in Image processing for INTELLIGENT VEHICLES TECHNOLOGIES and ROBOTICS. Different classification methods for both statistical and stochastical approaches will be presented.

Themen

  • * Introduction/Overview to Pattern Recognition
  • * Feature Selection ( Outlier Removal, Data Normalization , Missing data, Uncertainty Handling )
  • * Feature Generation ( Principal components analysis , Kernel Principal components analysis)
  • * 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

Schlagworte

Big Data

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

In the lecture we deal with various aspects of pattern recognition and their applications in Image processing for INTELLIGENT VEHICLES TECHNOLOGIES and ROBOTICS. Different classification methods for both statistical and stochastical approaches will be presented.

Themen

  • * Introduction/Overview to Pattern Recognition
  • * Feature Selection ( Outlier Removal, Data Normalization , Missing data, Uncertainty Handling )
  • * Feature Generation ( Principal components analysis , Kernel Principal components analysis)
  • * 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)

Prüfungsinformationen

Beurteilungskriterien/-maßstäbe

Project 50% + Homeworks 50%

Beurteilungsschema

Note/Grade Benotungsschema

Position im Curriculum

  • 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 2016
  • 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)