Accès direct au contenu


Version anglaise


Accueil > Formations > Master MVA > Présentation des cours

Probabilistic graphical models

Lecturer : Pierre Latouche (Descartes)  - Nicolas Chopin (ENSAE)

Objective of the course :

Provide a unifying introduction to probabilistic modelling through the framework of graphical models, together with their associated  learning and inference algorithms.

Topics :

  • Maximum likelihood
  • Linear regression
  • Logistic regression
  • Mixture models and clustering
  • Directed and undirected graphical models
  • Exponential family
  • Sum-product algorithm and exact inference
  • Hidden Markov models
  • Approximate inference
  • Bayesian methods

Prerequisites :

Course on Probability

Organization of courses :

  • 9 classes of 3 hours each
  • All classes and materials will be in English. All interactions, homeworks, exams may be done in French or English

Validation :

  •  3 homeworks with simple implementations of algorithms (Matlab, R, Python ou autre)
  •   1 final exam
  •   Reading a research paper and write a small report (less than 4 pages)
  • Si rattrapage: oral

    References :

    Chris Bishop. Pattern Recognition and Machine Learning. Springer, 2006

    More information...