Schnelleinstieg Reader


Startseite FSU

Statistical Learning Theory

This is class is about machine learning and some of its theoretical underpinnings. In the first part of the lecture we cover the classical topics of ordinary least squares regression, logistic regression and naive Bayes before we move on to the formal framework of PAC learning. In the latter parts of the lecture we will apply ideas from statistical learning theory to the analysis of support vector machines, nearest neighbor classification and random forests.

Suggested reading:

  • Christopher Bishop. Pattern Recognition and Machine Learning. Springer Verlag
  • Trevor Hastie, Robert Tibshirani, and Jerome Friedman.The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Springer Verlag
  • Andre Ng. Machine Learning. (lecture notes)
  • Shai-Shalev-Shwartz and Shai Ben-David. Understanding Machine Learning: From Theory to Algorithms. Cambridge University Press

Please register for this class through CAJ (only for registered users).