===== Foundations of discriminative learning and empirical risk minimisation =====


==== Overview ====


This teaching block provides fundamentals of discriminative learning and covers generalisation error bounds, empirical risk minimisation (ERM), and its consistency. It introduces the class of structured output SVMs and shows how to apply ERM based learning for models in this class.

  * **Teacher:** [[http://cmp.felk.cvut.cz/~xfrancv//|Dr. Vojtech Franc ]]

  * **Prerequisites:**
    * probability theory and statistics
    * linear algebra and optimisation
    * pattern recognition and decision theory

==== Lectures ====


^Topic ^Pdf ^Recording ^Notes ^
| **1. Empirical risk** | {{ :courses:be4m33ssu:er_print_ws2021.pdf | }} | [[http://ptak.felk.cvut.cz/recordings/flachbor/BE4M33SSU/BE4M33SSU-2021_1005-Franc-2.m4v | mp4 ]] | [1] Chap 2, [2] Chap 7 |
| **2. Empirical risk minimization** | {{ :courses:be4m33ssu:erm_print_ws2021.pdf | }}| [[http://ptak.felk.cvut.cz/recordings/flachbor/BE4M33SSU/BE4M33SSU-2021_1012-Franc-3.m4v| mp4 ]]| [1] Chap 2, [2] Chap 7 | 
| **3. Empirical risk minimization II** | {{ :courses:be4m33ssu:erm2_print_ws2021.pdf | }} | [[http://ptak.felk.cvut.cz/recordings/flachbor/BE4M33SSU/BE4M33SSU-2021_1019-Franc-4.m4v | mp4 ]]| [1] Chap 4, [2] Chap 12 |
| **4. Structured Output Support Vector Machines** | {{ :courses:be4m33ssu:sosvm_print_ws2021.pdf | }}| [[http://ptak.felk.cvut.cz/recordings/flachbor/BE4M33SSU/BE4M33SSU-2021_1026-Franc-5.m4v| mp4 ]]| [1] Chap 5, [2] Chap 12 |


==== Theoretical assignments ====
^Topic ^Pdf ^
| **Seminar: lecture 1 ** | {{ :courses:be4m33ssu:seminar_1_2021.pdf | }}|
| **Seminar: lecture 1,2 ** | {{ :courses:be4m33ssu:seminar_2_ws2021.pdf | }} |
| **Seminar: lecture 2,3 ** | {{ :courses:be4m33ssu:seminar_3_ws2021.pdf | }} |


==== Homework ====

Structured Output Perceptron {{ :courses:be4m33ssu:lab_so_perceptron_ws2021.pdf | task }}

==== Textbooks and References ====
    * [1] M. Mohri, A. Rostamizadeh and A. Talwalkar, Foundations of Machine Learning, MIT Press, 2012 [[https://pdfs.semanticscholar.org/e923/9469aba4bccf3e36d1c27894721e8dbefc44.pdf|[PDF]]]
     * [2] T. Hastie, R. Tibshirani and J. Friedman, The Elements of Statistical Learning, Springer, 2010 [[http://statweb.stanford.edu/~tibs/ElemStatLearn/printings/ESLII_print10.pdf|[PDF]]]