Preliminary Lecture Plan

The times for the lectures are preliminary and up for discussion to minimize overlap with other courses.

Slides will be linked from the lecture number in advance. For now, the slides from last version of the course are available to give a hint about the lecture content, but expect them to change shortly before the actual lecture is given.

Recomended reading refers to the textbook Linear Estimation.

Nr. When Where Content Slides Reading
1. 2023-09-19 15--17 Big conference room in Visionen
  • Least-squares (LS) estimation and the conditional mean.
  • Linear LS estimation and the special case of Gaussian random variables.
Sec. 3.1-3.2.4
article [1]
2. 2023-10-03 10-12 Big conference room in Visionen
  • Geometric interpretation of linear LS estimation.
  • Spectral factorization.
  • Discrete time causal Wienerfilters.
Sec. 3.3
(Bonus: Sec. 3.4-3.5)
Sec. 6.3-6.5
Sec. 7.3-7.7
3. 2023-10-17 10-12 Big conference room in Visionen
  • Bayes: Estimating an point or a density.
  • State-space models and Markov process.
  • Recursive Bayesian filtering.
  • Linear Gaussian models and the Kalman filter.
Lecture notes only
4. 2023-11-06 10-12 Big conference room in Visionen
  • The innovation process.
  • The Kalman filter from an innovation process perspective.
Sec. 4.1-4.2.4
Sec. 9.1-9.4
5. 2023-11-21 13-15 Big conference room in Visionen
  • Observability and controllability.
  • Time Invariance of the Kalman Filter.
  • Frequency Domain Expressions.
Sec. 1.5
Sec. 14.1-14.3
6. 2023-12-07 13-15 Big conference room in Visionen
  • Smoothing filters.
  • Information Form Kalman Filter.
  • Extended Kalman Filter (EKF).
Sec. 9.5-9.9
Sec. 10.1-10.4