Objectives of Programme's Learning Outcomes

• Have acquired highly specialised and integrated knowledge and broad skills in the various disciplines of computer science, which come after those within the Bachelor's in computer science.
• Master communication techniques.
• Communicate, both orally and in writing, their findings, original proposals, knowledge and underlying principles, in a clear, structured and justified manner.
• Develop and integrate a high degree of autonomy.
• Aquire new knowledge independently.
• Apply scientific methodology.
• Critically reflect on the impact of IT in general, and on the contribution to projects.

Learning Outcomes of UE

At the end of this UE, the student should have acquired theoretical knowledge and practical skills related to one of the major paradigms of AI: probabilistic models (probabilistic reasoning). He/she should :
- understand the importance and interest of the probabilistic perspective in AI.
- know the basic theory of probabilistic graphical models and Bayesian networks.
- know the hidden Markov models, particle filters, mixtures of Gaussians, the latent Dirichlet allocation, linear and non-linear Bayesian models.
- be able to put into practice statistical inference approaches.
- know how to use software libraries dedicated to probabilistic programming (PyMC, Pyro, etc.).
 

UE Content: description and pedagogical relevance

The UE is composed of one learning activities that exposes:
- artificial intelligence relying on probability theory, based on probabilistic graphical models, Bayesian networks, and their implementation through probabilistic programming.

This learning activity will include practicals to acquire the theory.

More details about the content are provided in the ECTS sheet of the learning activity.

Prior Experience

Not applicable