Author: Elmar Rueckert

image_pdfimage_print

190.001 Cyber-Physical Systems (2SH L, WS)

Elmar Rueckert teaching_pastlectures

This lecture provides a unique overview over central topics in Cyber-Physical-Systems:

  1. Kinematics, Dynamics & Simulation of CPS
  2. Data Representations  & Model Learning
  3. Feedback Control, Priorities & Torque Control
  4. Planning & Cognitive Reasoning
  5. Reinforcement Learning & Policy Search

The course provides a structured and well motivated overview over modern techniques and tools which enable the students to define learning problems in Cyber-Physical-Systems. 

Links and Resources

Optional Online Streaming:

Slides

Exam Preparation & Q&A’s

  • 13.01.2023 10:15 [Online only] Discussion of student questions regarding the exam. https://live.ai-lab.science/
  • 20.01.2023 10:15 [Online only] Course Feedback & Discussion of student questions regarding the exam. https://live.ai-lab.science/
  • 27.01.2023 10:15 [Online only] Discussion of student questions regarding the exam. https://live.ai-lab.science/
  • 30.01.2023 10:15 HS Thermoprozesstechnik Written Exam 
  • 06.03.2023 10:15 Location not fixed Written Exam (2nd option)

Last Year’s Slides:

Exam Dates

  • 30.01.2023 at 10:15 in HS Thermoprozesstechnik.
  • 06.03.2023 at 10:15 in HS Thermoprozesstechnik.
  • upon request via cps@unileoben.ac.at.

Location & Time

  • Location: HS Thermoprozesstechnik
  • Dates: Mondays, 10:15 – 12:00

Learning objectives / qualifications

  • Students get a comprehensive understanding of Cyber-Physical-Systems.
  • Students learn to analyze the challenges in simulating, modeling and controlling CPS.
  • Students understand and can apply basic machine learning and control  techniques in CPS.
  • Students know how to analyze the models’ results, improve the model parameters and can interpret the model predictions and their relevance.

Programming Assignments & Simulation Tools

For simulating robotic systems, we will use the tool CoppeliaSim. The tool can be used for free for research and for teaching. 

To experiment with state of the art robot control and learning methods Python will be used. If you never used Python and are unexperienced in programming, please visit the tutorials on Python programming prior to the lecture.  

The course will also use the tool Code With Me from JetBrains. With this stool, we can develop jointly code. 

Literature

  • The Probabilistic Machine Learning book by Univ.-Prof. Dr. Elmar Rueckert. 
  • Bishop 2006. Pattern Recognition and Machine Learning, Springer. 
  • Barber 2007. Bayesian Reasoning and Machine Learning, Cambridge University Press. 
  • Murray, Li and Sastry 1994. A mathematical introduction to robotic manipulation, CRC Press. 
  • B. Siciliano, L. Sciavicco 2009. Robotics: Modelling,Planning and Control, Springer.
  • Kevin M. Lynch and Frank C. Park 2017. MODERN ROBOTICS, MECHANICS, PLANNING, AND CONTROL, Cambridge University Press.

190.013 Introduction to Machine Learning Lab (2SH P, SS)

Elmar Rueckert teaching_pastlectures

This course accompanies the 190.012 Introduction to Machine Learning lecture.

Enrolling for this exercise is highly recommended but not a requirement for passing the machine learning lecture. 

Format, Location & Time

  • Format: The course format is physical attendance. 
  • Location: HS Kuppelwieser
  • Broadcast: WEBEX for the Q&A sessions
  • Dates: Fridays 13:15 – 14:45 Attention: There is one exception, on the 08.03.24, we start at 12:15!

Learning objectives / qualifications

Hands-on experience with machine learning methods. 

Course Resources

Everybody needs to sign in at MUOnline for the course. Access to Moodle will be essential for all participants in the course, as it will serve as the platform where course materials will be made available. 

Additional Course Resources

Python Videolectures and Tutorials

Contact

Melanie Neubauer via email at melanie.neubauer@unileoben.ac.at

190.012 Introduction to Machine Learning (2SH L, SS)

Elmar Rueckert teaching_pastlectures

This course is based on the Machine Learning book by Univ.-Prof. Dr. Elmar Rueckert. 

It is written for experienced undergraduates or for first
semester graduate students.

The lecture provides the basic knowledge for the application of modern machine learning methods. It includes an introduction to the basics of data modeling and probability theory. Classical probabilistic linear and non-linear regression methods are derived and discussed using practical examples.

Links and Resources

Location & Time

 

Slides

Course Topics

  1. Introduction to Machine Learning (Data and modelling fundamentals)
  2. Introduction to Probability Theory (Statistics refresher, Bayes Theorem, Common Probability distributions, Gaussian Calculus).
  3. Linear Probabilistic Regression (Linear models, Maximum Likelihood, Bayes & Logistic Regression).
  4. Nonlinear Probabilistic Regression (Radial basis function networks, Gaussian Processes, Recent research results in Robotic Movement Primitives, Hierarchical Bayesian & Mixture Models).
  5. Probabilistic Inference for Time Series (Time series data, basis function models, learning).

Learning objectives / qualifications

  • Students get a comprehensive understanding of basic probability theory concepts and methods.
  • Students learn to analyze the challenges in a task and to identify promising machine learning approaches.
  • Students will understand the difference between deterministic and probabilistic algorithms and can define underlying assumptions and requirements.
  • Students understand and can apply advanced regression, inference and optimization techniques to real world problems.
  • Students know how to analyze the models’ results, improve the model parameters and can interpret the model predictions and their relevance.
  • Students understand how the basic concepts are used in current state-of-the-art research in robot movement primitive learning and in neural planning.

Grading

The course will be graded based on a written exam (100 Points). 50% of all questions need to be answered correctly to be positive. The exam will take place in the classroom, or online, depending on the current university regulations.

In addition, up to 10 bonus points obtained in regular quiz sessions in the classroom, and 20% of the achieved points of the Machine Learning Lab will be added to your exam result. Note that bonus points can only be obtained when attending the lectures in person. 

Grading scheme: 0-49.9Pts (5), 50-65.9Pts (4), 66-79Pts (3), 80-91Pts (2), 92-100Pts (1).

Forthcoming exam dates are:

Literature

  • The Probabilistic Machine Learning book by Univ.-Prof. Dr. Elmar Rueckert. 
  • James-A. Goulet. Probabilistic Machine Learning for Civil Engineers. ISBN 978-0-262-53870-1.
  • Daphne Koller, Nir Friedman. Probabilistic Graphical Models: Principles and Techniques. ISBN 978-0-262-01319-2
  • Christopher M. Bishop. Pattern Recognition and Machine Learning. Springer (2006). ISBN 978-0-387-31073-2.
  • David Barber. Bayesian Reasoning and Machine Learning, Cambridge University Press (2012). ISBN 978-0-521-51814-7.
  • Kevin P. Murphy. Machine Learning: A Probabilistic Perspective. ISBN 978-0-262-01802-9

Note that all books are available at our library or at the chair of CPS. 

Adding a New Post Guidelines

Elmar Rueckert wiki_administrative, wiki_phds, wiki_technician, wiki_undergradsgrads

Clone an Existing Post

The best strategy is to clone an existing post. Filter all post by your target category. Select a post and clone it. 

Avoid Editing Simultaneously with Others a Post

Whenever you see the lock symbol, be careful. Contact the user first before you start editing the post. 

Click on Edit and Select the Categories & Featured Image

In the right panel, you see the categories list (left image below) and the featured image tab. 

Click on the publish button once you are done. 

User Proper Filenames for Images

Please always give your images a proper filename. That will make it easier for all to reuse images. 

 

Publish Your Post

Press the Publish button on the top right to save your post. Afterwards edit the content by pressing on the Elementor button in the center. 

Edit the Post in Elementor

We use the Elementor plugin to format our content. 

Use Titles, Inner Sections, Text Fields, Images, Videos and Shortcodes to present your content.

Adding Selected Publications to the Post

You can add publications to your post by pasting the following code into a shortcode element, enclosed by the parentheses [your code]

tplist include=”2,55,86″ entries_per_page=”5000″ image=”right” image_size=”150″ image_link=”self” template=”tp_template_2016″ link_style=”direct” as_filter=”true”

Make sure that you add the enclosing parentheses []!

The publication ids can be found in the publication list.

MATLAB Code of Probabilistic Movement Primitives for Motion Analysis

Elmar Rueckert research_software

Matlab Code Link

https://cps.unileoben.ac.at/wp/resources/code/MATLAB_ProbabilisticTrajectoryModel_2016Rueckert.zip

Publication where the Code was used

2016

Rueckert, Elmar; Camernik, Jernej; Peters, Jan; Babic, Jan

Probabilistic Movement Models Show that Postural Control Precedes and Predicts Volitional Motor Control Journal Article

In: Nature Publishing Group: Scientific Reports, vol. 6, no. 28455, 2016.

Links | BibTeX

Probabilistic Movement Models Show that Postural Control Precedes and Predicts Volitional Motor Control

MATLAB Code of Spiking Neural Networks for Robot Motion Planning

Elmar Rueckert research_software

Matlab Code Link

https://cps.unileoben.ac.at/wp/resources/code/MATLAB_SpikingNeuralPlanning_2016Rueckert.zip

Publication where the Code was used

2016

Rueckert, Elmar; Kappel, David; Tanneberg, Daniel; Pecevski, Dejan; Peters, Jan

Recurrent Spiking Networks Solve Planning Tasks Journal Article

In: Nature Publishing Group: Scientific Reports, vol. 6, no. 21142, 2016.

Links | BibTeX

Recurrent Spiking Networks Solve Planning Tasks

Stochastic Neural Networks for Robot Motion Planning

Elmar Rueckert research_videos

Video

Link to the file

You may use this video for research and teaching purposes. Please cite the Chair of Cyber-Physical-Systems or the corresponding research paper. 

Publications

2016

Tanneberg, Daniel; Paraschos, Alexandros; Peters, Jan; Rueckert, Elmar

Deep Spiking Networks for Model-based Planning in Humanoids Proceedings Article

In: Proceedings of the International Conference on Humanoid Robots (HUMANOIDS), 2016.

Links | BibTeX

Deep Spiking Networks for Model-based Planning in Humanoids

Rueckert, Elmar; Kappel, David; Tanneberg, Daniel; Pecevski, Dejan; Peters, Jan

Recurrent Spiking Networks Solve Planning Tasks Journal Article

In: Nature Publishing Group: Scientific Reports, vol. 6, no. 21142, 2016.

Links | BibTeX

Recurrent Spiking Networks Solve Planning Tasks