- 4MMIIA

Goal(s)

This 2nd year course aims to provide you with an overview of the goals and methods of artificial intelligence. It covers the theoretical and practical aspects of using machine learning models and symbolic reasoning through lectures and numerous lab sessions. The lab sessions focus on real-world applications in a variety of fields (biology, image processing, structured data).

Responsible(s)

Clovis GALIEZ

Content(s)

I. Introduction (1 lecture, 1 lab): overview, environmental and societal impacts; evaluation, metrics
II. Common models and algorithms (3 lectures, 3 labs): unsupervised (EM, K-means); supervised (SVM, kernel methods, random forest); regularization (principles, Ridge, Lasso)
III. Neural Networks (4 lectures, 4 labs): perceptron, gradient descent, backpropagation; CNN classification; U-Net segmentation; sequential data (RNN, LSTM); generative models
IV. Symbolic AI (4 lectures, 4 labs) ...

Programming: Python; for the practical assignments, students may use Python, R, or Prolog (familiarity with general programming and mathematical logic is required)
Mathematics: basics of probability and statistics, basics of linear algebra
Algorithms: concept of complexity

Test

Evaluation : 33% of Examen écrit and 67% of Examen écrit (3h)

Resit : 33% of Examen écrit (reported score) and 67% of Examen écrit (1h30)

Calendar

The course exists in the following branches:

• Curriculum - Core curriculum - Semester 7

Additional Information

Course ID : 4MMIIA
Course language(s):

You can find this course among all other courses.

Bibliography

Très bons livres de référence en apprentissage machine :
- An Introduction to Statistical Learning, James et al, https://www.statlearning.com/
- Pattern Recognition and Machine Learning, Christopher M. Bishop
- Spécifiquement sur le deep learning : https://www.deeplearningbook.org/
IA Symbolique : TBA