Für eine korrekte Darstellung dieser Seite benötigen Sie einen XHTML-standardkonformen Browser, der die Darstellung von CSS-Dateien zulässt.

News

You are here


Courses

Semester: 
Summer Term 2021
SWS/LP: 
4 SWS, 5 LPs
Recommended for: 
Master students in informatics and mechatronics interested in Machine Learning
Conditions: 
Prior knowledge in programming, basic mathematics, and machine learning, where the latter can be gained from different modules including statistical learning theory, artificial inteligence, or deep learning
News: 

To participate in this course, check out the moodle page at https://moodle.uni-siegen.de/course/view.php?id=24907

 
Turning Siegen into a painting - generated with https://deepart.io - based on the 2015 deep learning publication https://arxiv.org/abs/1508.06576

 

This module will present recent advances in machine learning in different fields of data sciences including imaging, vision, graphics, mechatronics, and sensorics. It addresses advanced techniques in the fields of machine learning, deep learning and artificial intelligence, with a particular focus on recent research papers, novel application areas and open questions in the aforementioned fields. Based on basic prior knowledge gained in other courses, this module specifically focuses on the state-of-the-art in machine learning by introducing recent publications from the leading international conferences on machine learning (e.g. NeurIPS, ICML, ICLR), computer vision (e.g. CVPR, ICCV, ECCV), or their application in fields like computer graphics, 3d reconstruction, robotics, navigation, medicine, or body-worn sensorics. After covering the theory of such works in the first half of the semester, a phase with challenges will ask every student to implement and apply one of the discussed techniques on their own in one of the leading machine learning frameworks in the second half of the semester. The results of the challenges need to be presented to the class, and a short final report on the challenge will be the courses examination. 

This will be an exciting interdisciplinary lecture for advanced master students from mechatronics and computer science!

More details can be found on the moodle page for this course at https://moodle.uni-siegen.de/course/view.php?id=24907


 
Let's make sensing smart!      
 
Semester: 
Summer Term 2021
Place/Time: 
Video lectures at moodle
SWS/LP: 
4+2 / 10
Recommended for: 
Master students in informatics with strong math background, math students
News: 

The course material will be accessible via moodle: https://moodle.uni-siegen.de/course/view.php?id=24905

Content of this lecture:
Being able to determine the argument that minimizes a (possibly nonsmooth) convex cost function efficiently is of great practical relevance. For example, convex variational methods are one of the most powerful techniques for many computer vision and image processing problems, e.g. denoising, deblurring, inpainting, stereo matching, optical flow computation, segmentation, or super resolution. Furthermore a clear understanding of convex optimization provides a baseline for further study of advanced non-convex or stochastic optimization techniques as encountered in deep learning, design or control problems.

In this lecture we will discuss first order convex optimization methods to implement and solve the aforementioned problems efficiently. Particular attention will be paid to problems including constraints and non-differentiable terms, giving rise to methods that exploit the concept of duality such as the primal-dual hybrid gradient method or the alternating directions methods of multipliers. This lecture will cover both the mathematical background, proving why the investigated methods converge, as well as their efficient practical implementation.

Convex Optimization

Example applications in computer vision and signal processing problems, including

  • Image denoising, deblurring, inpainting, segmentation
  • (Multinomial) logistic regression


Semester: 
Summer Term 2021
Lecturer: 
SWS/LP: 
5 Credits

Im Praktikum für Digitale Bildverarbeitung bearbeitet jeder Teilnehmer jeweils ein Projekt in welchem die Inhalte der Digitalen Bildverarbeitung praktisch, d.h. in Form eines in Python programmieren Programms, angewandt werden.

Dieses Semester besteht das zu bearbeitende Projekt aus der Implementierung einer graphischen Oberfläche, in welcher interaktiv zwei Bilder mittels der Poisson-Bildbearbeitung ("Poisson Image Editing") [1] nahtlos überblendet werden können. Hierzu werden wir insbesondere folgende Themen bearbeiten: GUI-Programmierung in Python: Interaktives Skizzieren einer Maske zur Segmentierung mittels lernbasierter Verfahren, Platzieren und Verschieben von Bildern auf der graphischen Oberfläche; Implementierung des Poisson Image Editing.

 

[1] Pérez, Patrick, Michel Gangnet, and Andrew Blake. "Poisson image editing." ACM SIGGRAPH 2003 Papers. 2003. 313-318.

Alle weiteren Informationen und Kursmaterialien werden auf Moodle hochgeladen: https://moodle.uni-siegen.de/course/view.php?id=24906

Semester: 
Winter Term 2020/2021
News: 

If you're interested in our Deep Learning course, you might also like the following Machine Learning courses offered by Joeran Beel, https://isg.beel.org/:

  • Project group "AutoML and Automated Algorithm Design, Selection & Configuration", 43ISG3401V
  • Seminar "Machine Learning Competition", 43ISG3301V

This course will be completely digital and is therefore hosted at moodle https://moodle.uni-siegen.de/course/view.php?id=21642.

Practice Manager: 
Semester: 
Winter Term 2020/2021
Lecturer: 
Place/Time: 
The course will be completely digital. All material will be uploaded to moodle.
SWS/LP: 
2+2SWS, 5 Credits
Recommended for: 
Master students in informatics interested in visual computing
News: 

To participate in this course, visit the moodle page at https://moodle.uni-siegen.de/course/view.php?id=23197.

Practice Manager: 

Semester: 
Winter Term 2020/2021
Lecturer: 
SWS/LP: 
2+2SWS, 5 Credits
News: 
Aufgrund der anhaltenden Corona-Pandemie und zum Schutz von Risikogruppen wird die digitale Bildverarbeitung dieses Semester digital stattfinden. Weitere Informationen finden Sie auf moodle: https://moodle.uni-siegen.de/course/view.php?id=23196

Segmentation

Digitale Bilder sind zur heutigen Zeit allgegenwertig und beinhalten häufig viele Informationen für den Betrachter. Diese Vorlesung beschäftigt sich mit der Entstehung, der Verarbeitung und der Repräsentation von digitalen Bildern. Es wird unter anderem die Rekonstruktion von digitalen Bildern behandelt, zu welcher beispielsweise das Entrauschen von verrauschten Bildern gehört, sowie die automatische Analyse digitaler Bilder, wie z.B. die Bildsegmentierung. Genauere Themen, die in diesem Kurs behandelt werden sind unter anderem:

  • Darstellung von digitalen Bildern
  • Bildentstehung
  • Bildinterpolation
  • Filter
  • Farbbilder und -transformationen
  • Segmentierungsverfahren
  • Clusterverfahren

In diesem Kurs wird es wöchentliche theoretische und praktische Aufgaben geben, deren Lösungen in den Übungen besprochen werden. Die Übungen werden dieses Jahr online und in Form von geleiteten Lernsessions stattfinden, in welchen Fragen gestellt werden können und Hilfe zu den Übungen angeboten werden. Weitere Informationen finden Sie auf moodle.

Bei Fragen bzgl. der Übungen bzw. der Vorlesung kontaktieren Sie bitte Hannah Dröge per E-Mail: hannah.droege@uni-siegen.de

Practice Manager: 
Semester: 
Summer Term 2020
Place/Time: 
Video lectures at https://moodle.uni-siegen.de/course/view.php?id=22080
SWS/LP: 
4+2 / 10
Recommended for: 
Master students in informatics with strong math background, math students
News: 

This semester, for the first time, the convex optimization lecture will be held jointly by Thorst Raasch and Michael Möller, representing an interdisciplinary effort between mathematics and computer science! To participate in this course, check out the moodle page at https://moodle.uni-siegen.de/course/view.php?id=22080

Content of this lecture:
Being able to determine the argument that minimizes a (possibly nonsmooth) convex cost function efficiently is of great practical relevance. For example, convex variational methods are one of the most powerful techniques for many computer vision and image processing problems, e.g. denoising, deblurring, inpainting, stereo matching, optical flow computation, segmentation, or super resolution. Furthermore a clear understanding of convex optimization provides a baseline for further study of advanced non-convex or stochastic optimization techniques as encountered in deep learning, design or control problems.

In this lecture we will discuss first order convex optimization methods to implement and solve the aforementioned problems efficiently. Particular attention will be paid to problems including constraints and non-differentiable terms, giving rise to methods that exploit the concept of duality such as the primal-dual hybrid gradient method or the alternating directions methods of multipliers. This lecture will cover both the mathematical background, proving why the investigated methods converge, as well as their efficient practical implementation.

Convex Optimization

Example applications in computer vision and signal processing problems, including

  • Image denoising, deblurring, inpainting, segmentation
  • (Multinomial) logistic regression
Fast Optimization Challenge

During the course of the lecture, we will pose a challenge to solve an optimization problem as quickly as possible. The best solution will receive a prize. The challenges will be a good preparation for the final exam!

Submission instructions: The source code should be sent via e-mail to michael.moeller@uni-siegen.de
 

Challenge: To be announced in the lecture
 

Leaderboard

Name Runtime Method
Michael Moeller 604 s Gradient descent (fixed step size)
     
     
Exam

The exam will be oral.

 


Semester: 
Summer Term 2020
Place/Time: 
Thursdays, 14:15 - 15:45 in H-F 116, Fridays 12:15 - 13:45 in H-F 112
SWS/LP: 
4 SWS, 5 LPs
Recommended for: 
Master students in informatics and mechatronics interested in Machine Learning
Conditions: 
Prior knowledge in programming, basic mathematics, and machine learning, where the latter can be gained from different modules including statistical learning theory, artificial inteligence, or deep learning
News: 

To participate in this course, check out the moodle page at https://moodle.uni-siegen.de/course/view.php?id=22049.

 
Turning Siegen into a painting - generated with https://deepart.io - based on the 2015 deep learning publication https://arxiv.org/abs/1508.06576

 

This module will present recent advances in machine learning in different fields of data sciences including imaging, vision, graphics, mechatronics, and sensorics. It addresses advanced techniques in the fields of machine learning, deep learning and artificial intelligence, with a particular focus on recent research papers, novel application areas and open questions in the aforementioned fields. Based on basic prior knowledge gained in other courses, this module specifically focuses on the state-of-the-art in machine learning by introducing recent publications from the leading international conferences on machine learning (e.g. NeurIPS, ICML, ICLR), computer vision (e.g. CVPR, ICCV, ECCV), or their application in fields like computer graphics, 3d reconstruction, robotics, navigation, medicine, or body-worn sensorics. After covering the theory of such works in the first half of the semester, a phase with challenges will ask every student to implement and apply one of the discussed techniques on their own in one of the leading machine learning frameworks in the second half of the semester. The results of the challenges need to be presented to the class, and a short final report on the challenge will be the courses examination. 

This will be an exciting interdisciplinary lecture for advanced master students from mechatronics and computer science!

More details can be found on the moodle page for this course at https://moodle.uni-siegen.de/course/view.php?id=22049


 
Let's make sensing smart!      
 
Semester: 
Summer Term 2020
Lecturer: 
Place/Time: 
Montags 10:00 - 13:00 Uhr und Dienstags 9:00 - 12:00 Uhr in H-A 7118
SWS/LP: 
5 Credits

Im Praktikum für Digitale Bildverarbeitung bearbeitet jeder Teilnehmer jeweils ein Projekt in welchem die Inhalte der Digitalen Bildverarbeitung praktisch, d.h. in Form eines in Python programmieren Programms, angewandt werden.

Dieses Semester besteht das zu bearbeitende Projekt aus der Implementierung einer graphischen Oberfläche, in welcher interaktiv zwei Bilder mittels der Poisson-Bildbearbeitung ("Poisson Image Editing") [1] nahtlos überblendet werden können. Hierzu werden wir insbesondere folgende Themen bearbeiten: GUI-Programmierung in Python: Interaktives Skizzieren einer Maske zur Segmentierung mittels lernbasierter Verfahren, Platzieren und Verschieben von Bildern auf der graphischen Oberfläche; Implementierung des Poisson Image Editing

 

[1] Pérez, Patrick, Michel Gangnet, and Andrew Blake. "Poisson image editing." ACM SIGGRAPH 2003 Papers. 2003. 313-318.
Semester: 
Winter Term 2019/2020
Lecturer: 
Place/Time: 
Lecture: Tuesday 10.15-12, in room HF 104/105, starting from Oct 8. Exercises: Friday 10.15-12, in room HC 6336/37, starting from Oct 11.
SWS/LP: 
2+2SWS, 5 Credits
Recommended for: 
Master students in informatics interested in visual computing
News: 

On Friday, 25.10.2019, there will be lecture by Professor Dr. Michael Möller in HC 6336/37 at 10.15

This course will give an introduction to basic numerical methods that you will need in the field of visual computing and well beyond.  Topics we will cover in the course include

  • Error analysis and the condition of a problem: How accurately can I expect to determine a solution?
  • Linear equations: How to solve them efficiently?
  • Linear regression: How do I fit a (linear) parametric model to some measured data?
  • Nonlinear equations: Using Newtons method to solve nonlinear equations.
  • Nonlinear optimization: How do I apply Newtons method to smooth optimization problems.
  • Computation of eigenvalues: Which algorithm allows me to compute the eigenvalues of a matrix?
  • Interpolation: How can I interpolate given data points with polynomials?
  • Integration: How do quadrature rules for numerical integration work?

The course will have weekly homework on the theory as well as the implementation of the methods we discuss. We will discuss the solution to the homework in the weekly exercises.  For any questions regarding the exercise or the lecture (including the password for the exercise page), please email Vaishnavi Gandikota at  (link sends e-mail)kanchana.gandikota@student.uni-siegen.de (link sends e-mail).

Besides the lecture slides I recommend the following sources for further readings

(English):

  • Press, W. H., Teukolsky, S. A., Vetterling, W. T., & Flannery, B. P. (2007). Numerical recipes 3rd edition: The art of scientific computing. Cambridge university press 
    (Very detailed introduction to numerical methods from a quite applied  perspective, available in the university library)
  • Kincaid, D., Kincaid, D. R., & Cheney, E. W. (2009). Numerical analysis: mathematics of scientific computing (Vol. 2). American Mathematical Soc.  
    (Also a very detailed reference manual, but with a mathematical perspective)
  • Turner, P. R., Arildsen, T., & Kavanagh, K. (2018). Applied Scientific Computing: With Python. Springer 
    (Introduction to numerical topics with examples in Python, electronically available via the university library)
  • Lecture Notes on Numerical Analysis (Peter J. Olver, University of Minnesota, 2008), available online  (link is external)

     

(German):

Practice Manager: 
Exercise operational: 

All information about the  exercise can be found at the exercise webpage.

Pages

Subscribe to RSS - Courses