1. komponenta

Lecture type	Total
Lectures	45

* Load is given in academic hour (1 academic hour = 45 minutes)

COURSE AIMS AND OBJECTIVES:
The aim of this course is to present key concepts and results, as well as basic techniques, approaches and tools of the modern statistical learning theory.

COURSE DESCRIPTION AND SYLLABUS:
The course covers the following topics: the concept of the statistical learning process, theory of consistency of the learning process, theory of estimating the rate of convergence of the learning process, methods for finding the optimal solution to the learning process, and analysis of algorithms of the statistical learning process.

1. Understanding machine learning, S. Ben-David, S. Shalew-Shwartz, Cambridge University Press, Cambridge, 2014.
2. Statistical learning theory, V. N. Vapnik, John Wiley & Sons, Inc., New York, 1998.
3. Foundations of Machine Learning, M. Mohri, A. Rostamizadeh, A. Tlwalkar, The MIT Press, Cambridge MA, 2018.
4. The elements of statistical learning, T. Hastie, R. Tibshirani, J. Friedman, Springe-Verlagr, New York, 2009.
5. The nature of statistical learning theory, V. N. Vapnik, Springer-Verlag, New York, 2000.
6. Neural Network Learning: Theoretical Foundations, M. Anthony, P. L. Bartlett, Cambridge University Press, Cambridge, 1999.

Ostali izborni predmeti - Regular study - Computer Science and Mathematics
Vezani kolegiji C - Regular study - Computer Science and Mathematics
Vezani kolegiji D - Regular study - Computer Science and Mathematics

Ostali izborni predmeti - Regular study - Computer Science and Mathematics
Vezani kolegiji C - Regular study - Computer Science and Mathematics
Vezani kolegiji D - Regular study - Computer Science and Mathematics