UE Machine learning fundamentals

Diplômes intégrant cet élément pédagogique :

Descriptif

  • Consistency of the Empirical Risk Minimization
  • Uniform Generalization Bounds and Structural Risk Minimization
  • Unconstrained Convex Optimization
  • Binary Classification algorithms (Perceptron, Adaboost, Logistic Regression, SVM) and their link with the ERM and the SRM principles
  • Multiclass classification
  • Application and experimentations

Evaluation : Homeworks (30%), Final exam (70%)

Pré-requis recommandés

Statistics and probability (BSc)

Compétences visées

Understanding of fundamental notions in Machine Learning (inference, ERM and SRM principles, generalization bounds, classical learning models, unsupervised learning, semi-supervised learning.

Informations complémentaires

Méthode d'enseignement : En présence
Lieu(x) : Grenoble
Langue(s) : Anglais