OMML 2018

Description

Optimization techniques are used in all kinds 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

Assistant: Ruggiero Seccia (office hours:  on email appointment)

Google group OMML_2018-19  Register to the group for receiveing info about the course (scheduling, timetable, teaching material etc.). Registration is possibile starting on September 24 until to October 31,  2018.

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

Topics 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 (WEKA, LIBSVM, R, TensorFlow)