Optimization for Learning, 9+3 credits

Course type

Advanced course

Periodicity

Irregular

Intended audience

Students who want to get an introduction to optimization for learning.

The course is based on the book Optimzation for Learning and Control. A more detailed description of the contents is given in the schedule.

Organization

There will be 12 lectures. The students are expected to participate in 4 exercise sessiones and solve 5 home work problems. There is also the possibility to carry out a non-mandatory project for an additional 3 credits. It is compulsory to attend the lectures and exercise sessions. There is no exam.

Lectures

First lecture is April 3, 10.15-12.00, Systemet, see schedule.

Ecercise Sessions

There are 4 exercise sessions, see schedule for more information.

Homeworks

All homeworks should be handed in at the lecture on paper. In addition to that matlab-files used for solving the homeworks should be sent as zipped files using e-mail to the examiner.

Homework 1 (Deadline 20240429)

You should solve Exercises 5.6 and 5.10

Homework 2 (Deadline 20240515)

You should solve Exercise 6.8

Homework 3 (Deadline 20240529)

You should solve Exercise 9.6

Homework 4 (Deadline 20240619)

You should solve Exercises 10.9 and 10.10

Homework 5 (Deadline 20240705)

You should solve Exercises 2.21, 2.22 and 12.2

Literature

The book Optimzation for Learning and Control. Slides for the lectures will be made available as pdf-files.

Examiner

Anders Hansson, Department of Electrical Engineering (anders.g.hansson@liu.se, phone: +46 703004401)