Descriptif
This course will introduce the theoretical and practical aspects of Statistical Machine Learning (ML) for the uninitiated. The course will cover the fundamental concepts of ML theory necessary to understand and implement ML algorithms and evaluate their performance on real problems. Through lectures, you will be presented with theoretical objects and notions, as well as presented with classical algorithms for classification, regression, and time series problems, including classical methods, kernel methods, and deep learning. Through IT practicals, you will be introduced to methodological keystones for using ML in the real world, including developing specialised coding skills and best practices. The course presumes familiarity with basic statistics notions and basic coding skills in Python.
Diplôme(s) concerné(s)
Parcours de rattachement
Format des notes
Numérique sur 20Littérale/grade réduitPour les étudiants du diplôme MScT-Data and Economics for Public Policy (DEPP)
Vos modalités d'acquisition :
The course will be evaluated through an individual final project. You will be asked to formulate an ML use-case on a dataset of your choice, investigate the statistical characteristics of your data, and implement relevant algorithms. You will be evaluated on the quality of your report and an oral defense with questions. We will look at the correctness of your application of material learnt in the course and at the critical perspective you have of your own work (e.g. limitations, assumptions made, practical relevance…).
Le rattrapage est autorisé (Max entre les deux notes)- Crédits ECTS acquis : 4 ECTS
La note obtenue rentre dans le calcul de votre GPA.
Pour les étudiants du diplôme MScT-Economics for Smart Cities and Climate Policy
Le rattrapage est autorisé (Max entre les deux notes)- Crédits ECTS acquis : 4 ECTS
La note obtenue rentre dans le calcul de votre GPA.