Course unit
Last updated: 26/09/2024
Edit
Course Director(s):
General Description:
Course instructor: Fabrice Muhlenbach
This course counts for 5 credits (/30 total for a semester). It gives the necessary mathematical background to perform data analysis using statistics, linear algebra and convex optimization. Practical sessions make use of the R-free software environment for statistical computing and graphics.
The following topics are covered:
- Basics in probabilities (chance experiments, random variables, moments, law of large number, …)
- Statistics (discrete and continuous distributions, estimates, Maximum Likelihood Estimation,...)
- Basics in linear algebra and in convex optimization
- Linear/polynomial/logistic Regression (closed-form solution, batch and stochastic gradient descent)
- Principal Component Analysis
- Clustering
Study materials:
- Pattern Recognition, S theodoridis, K. Koutroumbas, 4th edition
- Introduction to Statistics and Data Analysis, R. Peck, C. Olsen, J. Devore, Brooks/Cole, 4th edition, 2010.
- Convex Optimization, Stephen Boyd & Lieven Vandenberghe, Cambridge University Press, 2012.
- On-line Machine Learning courses: https://www.coursera.org/ UJM Semester 2 Expected prior-knowledge - Basic mathematics and statistics
Key words:
probability
Statistics
linear algebra
optimization
Linear regression
PCA
clustering
Number of teaching hours
60
Fields of study
Computer Science, Information Systems
Teaching language
English
Intended learning outcomes
| On completion of the unit, the student will be capable of: |
Classification level |
Priority |
Learning assessment methods
|
Percentage ratio of individual assessment
|
Percentage ratio of group assessment
|
|
Written exam:
|
66
|
%
|
Project submission:
|
|
%
|
|
Individual oral exam:
|
|
%
|
Group presentation:
|
|
%
|
|
Individual presentation:
|
|
%
|
Group practical exercise:
|
|
%
|
|
Individual practical exercise:
|
34
|
%
|
Group report:
|
|
%
|
|
Individual report:
|
|
%
|
|
|
|
|
Other(s): %
|
Programme and content
| Type of teaching activity |
Content, sequencing and organisation |
| Lectures |
(25h) |
| Supervised work |
(10h) |
| Labs |
(15h) |