IA et Données 1

Machine Learning and Data Sciences 1

Description: This course provides a structured introduction to the fundamental methods of artificial intelligence and machine learning (AI/ML), combining theoretical concepts with hands-on practice. It begins with an overview of general AI and machine learning concepts, including neural networks and supervised and unsupervised learning approaches. The foundations of deep learning are then developed, with particular emphasis on convolutional neural networks (CNNs) and their applications to complex data analysis. All these topics are covered through lectures and practical sessions designed to ensure students gain both conceptual understanding and practical experience with the tools.

The course also explores advanced topics such as reinforcement learning, uncertainty quantification, and physics-informed neural networks (PINNs). These approaches enable the treatment of optimization problems, sequential decision-making, and the modeling of physical systems while incorporating constraints derived from fundamental physical laws. Through case studies and hands-on exercises, the course highlights the potential of these methods for modeling, simulation, and analysis of complex systems in both science and engineering.

Bibliography:

  • Ref. [1] : J.N. Kurtz, Data-Driven Modeling & Scientific Computation: Methods for Complex Systems & Big Data, Oxford University Press (2013)

Learning outcomes: AA1: Understand the fundamental principles of AI and machine learning, including neural networks and supervised/unsupervised learning – AA2: Master deep learning and convolutional neural networks for complex data analysis – AA3: Apply reinforcement learning to optimization and sequential decision-making problems – AA4: Integrate uncertainty quantification into AI/ML models – AA5: Use physics-informed neural networks for modeling physical systems – AA6: Combine theory and practice through hands-on exercises and scientific or industrial case studies.

Evaluated skills:

  • Physical Modeling
  • Data Processing

Course supervisor:

  • Sylvie Le Hegarat
  • Emanuel Aldea

Geode ID: SPM-INF-025