OMML 2019

Description

Optimization techniques are used in most of machine learning problems. This course gives an overview of many concepts, techniques, and optimization algorithms in machine learning and statistical pattern recognition. We also touch theory behind these methods (e.g., optimality conditions and duality theory). We also discuss how to choose and to set up the right optimization methods for different machine learning applications.

Teacher: Laura Palagi

Teaching Assistant:Marco Boresta (office hours:  on email appointment)

Lecture calendar: check important dates on the calendar (last update September 27)

Google group OMML_2019-20  Register to the group for receiveing info about the course (scheduling, timetable, teaching material etc.). Registration is possibile starting on September 22 until to October 31,  2019.

Questionnaire for attending students: to be done the first day in the classroom (please note that you can partecipate just once and that the email will be registered and automatically added to the google group).

Syllabus may change from year to year to follow the more recent trends.

Topics surely include:

  1. Basics of learning theory (error functions; VC theory; margins).
  2. Supervised learning:
    • deep networks
    • support vector machines
  3. Use of standard software is discussed