FR
EN
Introduction au machine learningEA Big Data et IA (STI)
Introduction to Machine Learning
Teaching unit Advanced Track: Big Data and AI · S08T_BDA1 | EC Code S08A_BD1-1
6ECTS (EU)
1Coefficient
21:20Hours
Séquencement
Learning objectives
Deepen knowledge of artificial intelligence. To understand the theoretical and practical notions of artificial learning for massive data, in order to master the new principles and technologies of artificial intelligence.
Prerequisites
| Module | Teaching unit | Semester |
|---|---|---|
| Algorithms and Complexity | Programming Principles | S5 |
| Python Programming | Introduction to Systems and Networks | S5 |
Basic knowledge of linear algebra and proba/stat
Program
- Linear and non-linear regression/classification
- Probabilistic reasoning
- Artificial neuron networks
- Deep learning: convolutive networks, recurring networks,...
- Learning by strengthening
- Reduction of data dimensionality
- Unsupervised learning clustering
- Real case applications
Assessment
Final and mini-project review
References
- Azencott Chloé-Agathe, "Introduction au Machine Learning", Dunod edition.
- A. Cornuéjol, L. Miclet and V. Barra, "Artificial Learning", Eyrolles edition
- Stuart Russell and Peter Norvig, Artificial Intelligence, Pearson Eduction edition.
- Ian Goodfellow, Yoshua Bengio and Aaron Courville, Deep learning, MIT edition
Skills
5| Ref. | Verb | Description | Level |
|---|---|---|---|
| C1_2 | describe | and formalize information using probabilities | 2 |
| C1_2 | analyze | the results of a machine learning algorithm | 2 |
| C1_4 | design | design solutions to practical problems of strategies introduced during the course | 2 |
| C2_1 | identify | most appropriate learning process to solve a given problem | 2 |
| C2_2 | recognize | principles and techniques of machine learning | 3 |