227-0427-10L  Model-Based Estimation and Signal Analysis

SemesterFrühjahrssemester 2023
DozierendeH.‑A. Loeliger
Periodizitätjährlich wiederkehrende Veranstaltung
LehrspracheEnglisch


KurzbeschreibungThe course develops a selection of topics pivoting around state space models, factor graphs, and pertinent algorithms for estimation, model fitting, and learning.
LernzielThe course develops a selection of topics pivoting around state space methods, factor graphs, and pertinent algorithms:
- hidden-Markov models
- factor graphs and message passing algorithms
- linear state space models, Kalman filtering, and recursive least squares
- Gibbs sampling, particle filter
- recursive local polynomial fitting for signal analysis
- parameter learning by expectation maximization
- linear-model fitting beyond least squares: sparsity, Lp-fitting and regularization, jumps
- binary, M-level, and half-plane constraints in control and communications
SkriptLecture notes
Voraussetzungen / BesonderesSolid mathematical foundations (especially in probability, estimation, and linear algebra) as provided by the course "Introduction to Estimation and Machine Learning".