Logo ČVUT
CZECH TECHNICAL UNIVERSITY IN PRAGUE
STUDY PLANS
2023/2024

Statistical Modelling Lab

Login to KOS for course enrollment Display time-table
Code Completion Credits Range Language
NI-LSM KZ 5 3C Czech
Garant předmětu:
Kamil Dedecius
Lecturer:
Kamil Dedecius
Tutor:
Kamil Dedecius
Supervisor:
Department of Applied Mathematics
Synopsis:

The subject is oriented on a low-level approach to Bayesian statistical and information-theoretical modelling, where the student both learns the existing methods (regression models, Kalman filtering, models fusion, etc.) and tries to implement them. That is, instead of the (standard) intensive use of high-level libraries like pandas, scikit-learn or statsmodels, the stress is put on the use of numpy and scipy, as well as the low-level algebra and calculus. The second half of the semester is focused on the design of methods and algorithms, and analyses of their properties. At this point, the subject is on the border of own research and may result in the topic of final work (diploma or bachelor thesis).

Requirements:

BI-LIN, BI-ZMA

Ideally BI-PST too.

Syllabus of lectures:

1. Introduction into statistical modelling, Bayesian approach.

2. Linear model, prior and posterior information.

3. Sequential estimation, linear regression, varying parameters.

4. State-space models, filtering of states.

5. Model mixing and probabilistic mixtures.

6. Information divergences, Kullback-Leibler divergence, its use.

7. Project: Assignment.

8. Project: Analysis of the state of the art.

9. Project: Design of suitable solutions.

10. Project: Implementation of proposed solutions.

11. Project: Analysis of results.

12. Project: Assessment

Syllabus of tutorials:

1. Introduction into statistical modelling, Bayesian approach.

2. Linear model, prior and posterior information.

3. Sequential estimation, linear regression, varying parameters.

4. State-space models, filtering of states.

5. Míchání modelů a pravděpodobnostní směsi.

6. Information divergences, Kullback-Leibler divergence, its use.

7. Project: Assignment.

8. Project: Analysis of the state of the art.

9. Project: Design of suitable solutions.

10. Project: Implementation of proposed solutions.

11. Project: Analysis of results.

12. Project: Assessment

Study Objective:
Study materials:

1. Andrew Gelman et al., Bayesian Data Analysis, Chapman and Hall (2013), ISBN 1439840954.

2. David Barber, Bayesian Reasoning and Machine Learning, Cambridge University Press (2012), ISBN 978-0-521-51814-7.

Note:
Further information:
Course may be repeated
https://courses.fit.cvut.cz/NI-LSM/
Time-table for winter semester 2023/2024:
Time-table is not available yet
Time-table for summer semester 2023/2024:
Time-table is not available yet
The course is a part of the following study plans:
Data valid to 2023-11-30
Aktualizace výše uvedených informací naleznete na adrese https://bilakniha.cvut.cz/en/predmet6098006.html