English

Français

English

Français

Appearance

Artificial intelligence and simulation (09_O-IAS) ​

  • Coefficient : 6
  • Hourly Volume: 150h (including 72h supervised)
    CM : 27h supervised
    Labo : 45h supervised (and 12h unsupervised)
    Out-of-schedule personal work : 66h
  • Including project : 6h supervised and 18h unsupervised project

AATs Lists

Description ​

Introduce you to the basic techniques of artificial intelligence and explore a theme of your choice in more depth through a project. The majority of themes are approached from the angle of their applications, and are associated with practical work.

  1. Knowledge Representation
    • Deduction in Classical Logic, Logics for the Representation of Knowledge (modalities, actions and change)
    • Logic Programming
    • Fuzzy logic and its application to fuzzy control
  2. Data Science – Artificial Learning
    • Data mining
    • Classification
    • Neural networks
    • Reinforcement learning
  3. Applications of artificial intelligence
    • Video games
    • Autonomous robotics
    • Natural language processing
    • Carrying out a project independently

Learning Outcomes AAv (AAv) ​

  • AAv1 [heures: 10, E1, F1] : At the end of the first period of the module, students will be able to organize the different concepts, methods and techniques of Artificial Intelligence and to situate and compare them. in relation to each other.
  • AAv2 [heures: 20, B1, B2] : At the end of the module, students will be able to name and explain the most appropriate knowledge representation models for the formulation and resolution of characteristic problems varied.
  • AAv3 [heures: 30, C2, C3] : At the end of the module, students will be able to propose, design and implement a system solving a given problem using a given AI technique.
  • AAv4 [heures: 30, D2, B2] : At the end of the module, students will be able to implement different tools and existing software libraries linked to AI for the industrial application areas covered.
  • AAv5 [heures: 20, C4, F1] : At the end of the module, students will be able to analyze and evaluate the performance of an AI system, and to identify and take into account potential biases and limitations.
  • AAv6 [heures: 40, C1, C3, D1, F2, G1] : At the end of the module, students will be able to work in a team and independently in the design and implementation of a system solving a given problem using appropriate AI techniques of their choice.

Assessment methods ​

The assessment is done through a continuous assessment (at least 3 knowledge checks) and a pair project, with the possibility of catching up on one of the continuous assessment notes.

Key Words ​

Logics, knowledge representation and logic programming, fuzzy logic and control, neural networks, reinforcement learning, deep learning, data science, natural language processing (NLP).

Prerequisites ​

Programming in python and an object-oriented language. Classes may be taught in English

Resources ​

  • Course and tutorial materials (in English)
  • Thematic bibliographies for each theme
  • Stuart Russell and Peter Norvig. Intelligence artificielle. Addison-Wesley, 2010
  • Richard S Sutton and Andrew G Barto, Reinforcement learning : An introduction, 2014.
  • Collectif. L'intelligence artificielle. De quoi s'agit-il vraiment ? Editions Cépaduès, 2020.