Statistical Signal Processing
Information
| Teacher coordinator | Romain Hérault |
| Teacher(s) | Romain Hérault |
| Language | English |
| Credits | 4.5 |
| Teaching | Lectures : 21h Exercises : 21h |
| Option | Data science |
| Web site | https://moodle.insa-rouen.fr/enrol/index.php?id=942 |
Aim and objective
In this lecture, signal processing problems will be addressed in a machine learning point of view.
Outcome learning
- INSA reference data :
- Obtenir une description statistique d'un ensemble de données [3P]
- Filtrer et modéliser des signaux [3P]
- CNISF reference data :
- H30T [3P]
- J40K [1P]
- J10P [3P]
Course description
- Random Signals
- Stochastic Linear Systems
- Bayesian filtering and smoothing
- Kalman filtering and smoothing
- Particle filtering and smoothing
- Hidden Markov Model
- Change point detection
- Project based on the reading and implementation of a journal paper
Prerequisites
- Statistics and Numerical Analysis,
- Signal Processing,
- Numpy, Python programmation
Bibliography
- mo Särkkä (2013). Bayesian Filtering and Smoothing. Cambridge University Press.
- R.E. Elliott, L. Aggoun and J.B. Moore, Hidden Markov Models: Estimation and Control, Springer-Verlag, 1995
Assessment
- Final Exam: 50%
- In-class evaluation and project: 50%
