FR
EN
Machine LearningDécision (GSI)
5ECTS (EU)
2Coefficient
34:00Hours
Séquencement
Learning objectives
- Consider the problem of supervised and unsupervised learning from a probabilistic and statistical perspective.
- Apply these modelling principles in linear models and neuron networks.
- Be able to implement associated algorithms in an interpreted programming language.
Prerequisites
| Module | Teaching unit | Semester |
|---|---|---|
| Algorithms and Programming 3 | Basic Sciences 3 | S3 |
| Mathematics 1.1 | Basic Sciences 1 | S1 |
| Mathematics 1.2 | Basic Sciences 1 | S1 |
| Algorithms and Programming 1 | Optional Constitutive Elements 1 | S1 |
| Mathematics 2.1 | Basic Sciences 2 | S2 |
| Mathematics 2.2 | Basic Sciences 2 | S2 |
| Algorithmics and Programming | Basic Sciences 2 | S2 |
| Probabilities and statistics | Mathematics and Computer Science 1 | S5 |
| Object-oriented programming C++ | Mathematics and Computer Science 1 | S5 |
| Mathematics 3.1 | Basic Sciences 3 | S3 |
| Mathematics 3.2 | Basic Sciences 3 | S3 |
| Mathematics 4.1 | Basic Sciences 4 | S4 |
| Probabilities and Statistics | Engineer's Tools S5 | S5 |
Program
- Introduction
- Probabilistic modelling and statistical inference
- Linear models for regression and classification
- Neuron networks for regression and classification
- Mixture and clustering models
Assessment
4 TP rated: 25%, 25%, 25%, 25%
References
- Christopher M. Bishop, Pattern Recognition and Machine Learning, Springer-Verlag New York 2006
- Lindholm, Andreas, et al. Machine Learning: A First Course for Engineers and Scientists. Cambridge University Press, 2022.
- Murphy, Kevin P. Probabilistic machine learning: an introduction. MIT press, 2022.
Skills
4| Ref. | Verb | Description | Level |
|---|---|---|---|
| C2_1 | analyze | Mastering the principles of random modelling useful for machine learning and understanding their limitations | 2 |
| C2_1 | analyze | Have theoretical and practical knowledge of linear models for learning | 2 |
| C2_1 | analyze | analyze, understand neuron network models and how their parameters can be learned | 2 |
| C2_1 | analyze | analyze, Understand some clustering techniques from the unifying angle of Gaussian mixing models | 2 |