Data Mining and Learning Methods

Information

Teacher coordinatorRomain HĂ©rault
Teacher(s)Romain Hérault, Stéphane Canu
LanguageEnglish
Credits4.5
TeachingLectures : 18h Exercises : 18h
OptionData science
Web sitehttps://moodle.insa-rouen.fr/course/view.php?id=200

Aim and objective

The purpose of this lecture is to familiarize the student with learning and data mining methods on huge amount of data.

Outcome learning

  • INSA reference data :
    • Concevoir un système d'ingĂ©nierie des donnĂ©es [3P]
    • DĂ©terminer des classes de problèmes [3P]
  • CNISF reference data :
    • J40K [1P]
    • J10C [2I]
1 - Notion, 2 - Concept, 3 - Application, I - fully, P - incomplete

Course description

  • Non linear methods for data mining
  • Markov models
  • Kernel machine
  • Artificial Neural Network
  • Decision tree and forest
  • Classifier mixing

Prerequisites

  • Data mining

Bibliography

  • Trevor Hastie, Robert Tibshirani and Jerome Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction, springer, 2001
  • John Shawe-Taylor and Nello Cristianini Kernel Methods for Pattern Analysis, Cambridge University Press, 2004
  • Bernhard Schölkopf and Alex Smola. Learning with Kernels. MIT Press, Cambridge, MA, 2002.

Assessment

  • Project: 40%
  • Final Exam: 60%