Course syllabus adopted 2022-02-03 by Head of Programme (or corresponding).
Overview
- Swedish nameMaskininlärning av dynamiska system med systemidentifiering
- CodeSSY230
- Credits7.5 Credits
- OwnerMPSYS
- Education cycleSecond-cycle
- Main field of studyAutomation and Mechatronics Engineering, Electrical Engineering
- DepartmentELECTRICAL ENGINEERING
- GradingTH - Pass with distinction (5), Pass with credit (4), Pass (3), Fail
Course round 1
- Teaching language English
- Application code 35127
- Block schedule
- Open for exchange studentsNo
Credit distribution
Module | Sp1 | Sp2 | Sp3 | Sp4 | Summer | Not Sp | Examination dates |
|---|---|---|---|---|---|---|---|
| 0108 Examination 4.5 c Grading: TH | 4.5 c |
| |||||
| 0208 Laboratory 3 c Grading: UG | 3 c |
In programmes
Examiner
Jonas Sjöberg- Full Professor, Systems and Control, Electrical Engineering
Eligibility
General entry requirements for Master's level (second cycle)Applicants enrolled in a programme at Chalmers where the course is included in the study programme are exempted from fulfilling the requirements above.
Specific entry requirements
English 6 (or by other approved means with the equivalent proficiency level)Applicants enrolled in a programme at Chalmers where the course is included in the study programme are exempted from fulfilling the requirements above.
Course specific prerequisites
Basic knowledge in automatic control, statistics, signals and systems.Aim
The course aims to give the fundamental theory of identification of dynamical systems, i.e. how to use measured input-output data to build mathematical models, typically in terms of differential or difference equations. Further, the course aims to give fundamental knowledge of statistical learning, machine learning algorithms estimating relations in data, with the focus on dynamical systems.
Learning outcomes (after completion of the course the student should be able to)
- understand and explain fundamental aspects on statistical learning and relate these to the estimation of dynamical systems
- understand and explain the properties of the input signals for an identification experiment and how it influence the quality of the estimated model.
- understand and explain the possibilities and limitations concerning the quality of estimated models and on which factors these limitations depend.
- understand and explain properties of different model structures and identification methods.
- understand and use methods for validating estimated models.
- understand and use computer tools for system identification.
Content
The course includes:- Fundamentals on statistical learning where functions are estimated from data
- The mathematical foundations of System Identification
- Choice of model structure Linear and nonlinear models
- Non-parametric techniques
- Parametrizations and model structures
- Parameter estimation
- Asymptotic statistical theory
- User choices
- Experimental design
- Recursive identification and adaptive control
Organisation
The course comprises lectures and a number of hands on assignments/laboratory experiments that address important parts of the course.Literature
- Chapter 1-3 of An Introduction to Statistical Learning, Gareth James, Daniela Witten, Trevor Hastie, Robert Tibshirani, Springer. Freely available as pdf: http://www-bcf.usc.edu/~gareth/ISL/ (Links to an external site.).
- System Identification, by Söderström & Stoica Download System Identification, by Söderström & Stoica . This book is very good in explaining the basic theory. Most topics we cover in the course can be found here.
- Alternative literature: System Modeling & System Identification, Rolf Johansson, available at Cremona (STORE).
Examination including compulsory elements
Examination is based on written exam, grading scale TH, and passed assignment/laboration.The course examiner may assess individual students in other ways than what is stated above if there are special reasons for doing so, for example if a student has a decision from Chalmers on educational support due to disability.