This course offers a comprehensive introduction to digital signal processing. Students will build
the mathematical and conceptual foundations of signal analysis, then apply them to sampling,
filtering, and frequency-domain techniques, laying the groundwork for state estimation methods.
- Enseignant: Sarra DEHILI
The Introduction to Machine Learning (IML) course, coded as UEF1.2.1 and taught in Semester 2 , offers a comprehensive foundation in ML with a specific focus on its applications in robotics and control systems. This 4-credit module balances theoretical lectures (1h30) with practical laboratory sessions (2h30) , aiming to provide students with hands-on experience using frameworks like NumPy, pandas, and scikit-learn. The curriculum spans from supervised learning techniques like Linear Regression and SVM to unsupervised methods such as K-means and PCA , while also covering Neural Networks and Reinforcement Learning (RL) for tasks like path planning and autonomous vehicle control. Advanced topics include Model Predictive Control (MPC) , sensor data processing for LiDAR and cameras , and the ethical considerations of AI. Students are evaluated through laboratory reports (40%) and a final exam (60%) , supported by high-level resources such as Andrew Ng’s Coursera course and textbooks by Bishop and Goodfellow
- Enseignant: Belal Alshaqaqi
Le cours concerne l'application de la MEF dans la conception des structures.
- Enseignant: Faiza Boumediene