This semester the seminar will be devoted to an introduction to the foundations, theory and practice of machine learning.

Text:

The first half of the seminar will be mostly based on An Introduction to Computational Learning Theory by Michael Kearns and Umesh Vazirani (abbreviated KV), and the notes by Avrim Blum (abbreviated B), and Amnon Shashua (abbreviated S).

Another source of material is Machine Learning, by Tom Mitchell, McGraw Hill, 1997 (abbreviated M).

Lecture Plan

  1. 09/11. Ziv Ben-Eliahu and Shai Sharabi: The consistency model, the mistake-bound model, the weighted majority algorithm, B2, B3, S1 .
  2. 14/11. Guy Karlebach and Natalia Yakimovits: The Perceptron and Winnow algorithms. B4, S3 .
  3. 21/11. Elad Horev: The PAC model. KV1. and B5.
  4. 28/11. Guy Shattah. Occam's razor. KV2,and B6.
  5. 05/12. Roi Krakovsky: Learning finite automata by experimentation: Angluin's algorithm. KV8.
  6. 12/12. Alex Churkin. VC-dimension, KV3, and B7-slides and B7-notes
  7. 19/12. Shai Zakov. VC-dimension,continued, B8 .
  8. 26/12. David Gabbay: Support Vector Machines. C.J.C. Burges, "A Tutorial on Support Vector Machines for Pattern Recognition", Data Mining and Knowledge Discovery, Vol. 2, Number 2, p. 121-167, Kluwer Academic Publishers, 1998 S4. B25 S4.
  9. 02/01. Guy Ben-Yosef. Bayesian learning, M6.
  10. 09/01. and Yoav Goldberg. Bayesian learning, continued.
  11. 26/01. Shahar Michal . Expectation Maximization.
  12. 23/01. and Tor Ivry. Expectation Maximization, continued.

Administration