This course provides a clear path from the mathematical foundations of AI to its practical use in industry. First, it examines the most important mathematical ideas, such as linear algebra, calculus, and probability theory. These are all very important for understanding algorithmic logic. Students then move on to Machine Learning (ML), where they learn algorithms for classification, regression, and clustering. A special part of the course is dedicated to artificial neural networks (ANNs), where students will learn about deep learning architectures such as perceptrons and multi-layer networks, which are used to solve non-linear problems. By linking theory with practice, students can develop skills in machine learning methods for classification and regression tasks, before exploring artificial neural networks for advanced pattern recognition. The course focuses on practical problem-solving, using real industrial scenarios. By using tools like Python and TensorFlow, students learn to create and run working models (complete AI systems) that turn raw data into useful information.
- Enseignant: Hocine MERABTI