Hauptstudium  

Pattern Recognition and Neural Networks

The lecture gives an introduction to statistical pattern recognition, where neural networks and their relation to statistical classifiers will also be discussed.

Type
 Dates/Rooms Start Instructor
V4 Mo, 10:00h - 11:30h 2356|051 (AH VI)
Mi, 09:30h - 11:00h 2356|050 (AH V) 		19/10/2009 Prof. Dr.-Ing. H. Ney
Ü2 Mi, 14:00 - 15:30 2356|056 (5056) 21/10/2009 Martin Ratajczak; Simon Wiesler

Requirements

basic knowledge on probability calculus / statistics

News

  • The submission date for exercise sheet 10 has changed: January, 13th 2010
  • Registration for the exercise is needed, see FAQ.

    • Contents

    • basic statistics
    • training and learning
    • model-free approaches
    • neural networks and discriminative training
    • error integral: characteristics and estimates
    • mixture distributions and cluster analysis
    • EM-algorithm and hidden Markov models
    • feature extraction and linear mappings

    Lecture Notes (Access only permitted within the RWTH domain)

    • Overview of i6: Research and Courses  
    • Lecture Notes (SS 05, English)    
    • Lecture Notes (SS 02, German)    
    • Appendix: Support Vector Machines, Logistic Regression, and Log-linear Models (SS 07, English)  
    • Appendix: Maximum Entropy (WS 00/01, English)    

    FAQ

    • Does this lecture count as a practical or a theoratical course (for diploma students)? As specified in the Campus system the lecture is a practical course.
    • Do I have to register for this course? Please register for the Exercises 20.11.2009 (via the CampusOffice system). Bachelor and Master students also have to register at the ZPA. Please arrange an appointment for the oral exam with Prof. Ney before you register at the ZPA.

    Software

    Exercises

    You are strongly suggested to solve the tasks and hand in your solutions in groups of two to three students.
    • 1. Exercise Sheet (Submission: October, 28th 2009)    
    • 2. Exercise Sheet (Submission: November, 4th 2009)    
    • 3. Exercise Sheet (Submission: November, 11th 2009)    
    • 4. Exercise Sheet (Submission: November, 18th 2009)    
    • 5. Exercise Sheet (Submission: November, 27th 2009)    
    • 6. Exercise Sheet (Submission: December, 2nd 2009)    
    • 7. Exercise Sheet (Submission: December, 9th 2009)    
      • ( The solution of excercise sheet 5 needs the library LAPACK: http://www.netlib.org/lapack )
    • 8. Exercise Sheet (Submission: December, 16th 2009)    
    • 9. Exercise Sheet (Submission: December, 23rd 2009)    
    • 10. Exercise Sheet (Submission: January, 13th 2010)    
    • 11. Exercise Sheet (Submission: January, 20th 2010)    
    • 12. Exercise Sheet (Submission: January, 27th 2010)