SubjectsSubjects(version: 945)
Course, academic year 2023/2024
   Login via CAS
Mathematical foundations of machine learning - NMAG469
Title: Mathematical foundations of machine learning
Guaranteed by: Mathematical Institute of Charles University (32-MUUK)
Faculty: Faculty of Mathematics and Physics
Actual: from 2021
Semester: winter
E-Credits: 3
Hours per week, examination: winter s.:2/0, Ex [HT]
Capacity: unlimited
Min. number of students: unlimited
4EU+: no
Virtual mobility / capacity: no
State of the course: taught
Language: English
Teaching methods: full-time
Teaching methods: full-time
Additional information: https://users.math.cas.cz/~hvle/ML2022advertisement.pdf
Guarantor: Hong Van Le, Ph.D.
Class: M Mgr. MSTR
M Mgr. MSTR > Volitelné
Annotation -
Last update: Mgr. Dalibor Šmíd, Ph.D. (13.05.2022)
In Machine Learning one develops mathematical methods for modeling data structures, which express dependency between observables, and designs efficient learning algorithms for estimation of such dependency. The most advanced part of Machine Learning is statistical learning theory that takes into account our incomplete information of observables, using probability theory, or preferably, using measure theory and functional analysis. In this way we not only unveil hidden structure of data but also make a prediction for the future.
Course completion requirements -
Last update: Hong Van Le, Ph.D. (12.09.2021)

1. Getting involved is a prerequisite for participate in the exam.

2. Questions in the exam correspond to the syllabus of the subject to the extent it was presented at the lecture.

Alternatively, students can choose a term paper assignment.

3. The final mark takes account for an active participation in the lecture.

Literature -
Last update: Hong Van Le, Ph.D. (12.09.2021)

1. S. Shalev-Shwart and S. Ben-David, Understanding Machine Learning:

From Theory to Algorithms, Cambridge University Press, 2014.

2. M. Mohri, A. Rostamizadeh, A. Talwalkar, Foundations of Machine Learning,MIT Press, second Edition, 2018.

3. L. Deveroye, L. Gy\"orfi and G. Lugosi, A Probabilistic Theory of Pattern Recognition, Springer 1996.

4. Lecture notes ``Mathematical foundations of machine learning"

Syllabus -
Last update: Hong Van Le, Ph.D. (12.09.2021)

1. Statistical models of machine learning.

2. Supervised learning, unsupervised learning.

3. Generalization ability of machine learning.

4. Neural networks and deep learning.

5. Bayesian machine learning and Bayesian networks.

 
Charles University | Information system of Charles University | http://www.cuni.cz/UKEN-329.html