Institute of Computer Science
  1. Courses
  2. 2018/19 spring
  3. Machine Learning II (LTAT.02.004)
ET
Log in

Machine Learning II 2018/19 spring

Previous years: 2008 » 2012 » 2013 » 2014

  • Main
  • Lectures
  • Exercise sessions
  • Grading
  • Piazza forum
  • Upload

IV. Introduction to Optimization

Given by Ilya Kuzovkin
Materials by Konstantin Tretyakov

Brief summary: Optimization problem statement and basic terminology (minimum, maximum, gradient, Hessian). Classical methods for unconstrained optimization - gradient descent, stochastic gradient descent, Newton's method. Brief overview of constrained optimization.

Slides: PDF

Auxiliary reading: PDF

Literature: Wikipedia has some good articles on the topic. Otherwise, pick any fat textbook with "Optimization methods" in the title.

Video: panopto.ut.ee (2014)

  • Institute of Computer Science
  • Faculty of Science and Technology
  • University of Tartu
In case of technical problems or questions write to:

Contact the course organizers with the organizational and course content questions.
The proprietary copyrights of educational materials belong to the University of Tartu. The use of educational materials is permitted for the purposes and under the conditions provided for in the copyright law for the free use of a work. When using educational materials, the user is obligated to give credit to the author of the educational materials.
The use of educational materials for other purposes is allowed only with the prior written consent of the University of Tartu.
Terms of use for the Courses environment