Teaching
Please note that I taught all the following courses in French.
Summary of taught courses
| Courses | Level | Year | Type | Hourly volume |
|---|---|---|---|---|
| Statistics | INSA: GM4 | 2019 & 2020 | CM/TD/TP | 42H x 2 |
| Projet on machine learning | UVS: M2 | 2021 | CM/TP | 27H |
| Inferential Statistics | INSA: GM3 | 2020 & 2021 | TD/TP | 30H x 2 |
| Matrix Computation | INSA: ITI3 | 2019 & 2020 | TD/TP | 21H x 2 |
| Mathematics refresher course | INSA: ITI3 | 2019 & 2020 | CM/TD | 21H x 2 |
| Introduction to machine learning | INSA: ESD | 2020 | CM/TP | 21H |
| Mathematics refresher course | INSA: ESD | 2019 & 2020 | CM/TD | 21H x 2 |
| Total | INSA 2019–2020: 156H | INSA 2020–2021: 192H | UVS 2021: 21H |
Acronyms GM, UVS, ITI and ESD stand respectively for Génie Mathématiques, Université Virtuelle du Sénégal, master en Big Data, Informatique et Technologie de l’Information, Expert en Sciences des Données. Also, CM, TP and TD means, respectively, lecture, directed work, practical work.
Some details about taught courses
Statistics
- Head: Bruno Portier
- Number of students: 72 students in 2019 and 78 in 2020.
- Work provided: Ensure CM/TD/TP (R software), correct the exam papers and participate to defenses.
- Content: this course was centered around the theme of the Linear Model and included the following chapter:
- descriptive study of time series;
- simple and multiple Gaussian linear model;
- 1-factor analysis of variance;
- 2-factor analysis of variance.
Matrix Computation
- Head: Gilles Gasso.
- Number of students: about 30 students per group.
- Work provided: ensure TD and TP (with the Octave software).
- Contents: the aim of this course is to initiate students to the problems related to the use of numerical methods to solve engineering problems. It included the following courses:
- solving linear systems with application to least squares problems; - matrix factorization: LU, with pivot, Cholesky, QR;
- iterative methods: Jacobi, Gauss-Seidel and relaxation;
- methods for computing eigenvalues and singular values.
Introduction to machine learning
- Head: Bruno Portier.
- Number of students: 19.
- Work provided: ensure CM, TD and TP (with the Python software).
- Contents: the aim of this course was to introduce the participants to the field of machine learning. It took place over 3 days of 7 hours and consisted of the following chapter
- introduction to data science: examples of applications, typology of statistical learning problems, supervised learning (the main concepts), model selection and validation;
- introduction to dimension reduction methods;
- introduction to clustering methods.
Project in machine learning
- Head: Seydina Moussa Ndiaye.
- Number of students: 21.
- Work provided: design and provide CM/TP (Python software).
- Content: the objective of this course was to implement and validate solutions, following an initial specification, of a machine learning project. It consists in predicting the price of an apartment through multiple regression, variable selection methods and Ridge and Lasso regularized regressions.
Mathematics refresher course (ITI3)
- Head: Benoit Gaüzère
- Number of students: about 10.
- Work provided: to ensure the CM/TD.
- Contents: the aim of this module was to resume some notions of Mathematics to allow the students to follow more easily the signal processing and numerical methods for the engineer courses. It consisted of the following chapter:
- linear algebra: matrix factorization (LU, with pivot, Cholesky, QR), iterative methods for solving a linear system;
- real analysis and complex numbers: integral and derivative calculus, Fourier and Laplace transforms.