Machine Learning 1

Garant předmětu:

Daniel Vašata

Přednášející:

Rodrigo Augusto Da Silva Alves, Daniel Vašata

Cvičící:

Rodrigo Augusto Da Silva Alves, Daniel Vašata

Předmět zajišťuje:

katedra aplikované matematiky

Anotace:

The goal of this course is to introduce students to the basic methods of machine learning. They get theoretical understanding and practical working knowledge of regression and classification models in the supervised learning scenario and clustering models in the unsupervised scenario. Students will be aware of the relationships between model bias and variance, and know the fundamentals of assessing model quality. Moreover, they learn the basic techniques of data preprocessing and multidimensional data visualization. In practical demonstrations, pandas and scikit libraries in Python will be used.

Požadavky:

The knowledge of calculus, linear algebra and probability theory is assumed.

Osnova přednášek:

1. Introduction and basic concepts of Machine Learning

2. Supervised learning setup, Linear regression - Ordinary least squares

3. Linear regression - geometrical interpretation, numerical issues

4. Ridge regression, bias-variance trade-off

5. Classification setup, Decision trees

6. Ensemble methods (Random forests, Adaboost)

7. K-nearest neighbors for classification and regression

8. Logistic regression

9. Model evaluation, cross-validation

10. Feature selection

11. Unsupervised learning setup, Association rules

12. Hierarchical clustering, the k-means algorithm

Osnova cvičení:

1. Introduction, Python and jupyter notebooks

2. Supervised learning setup, Linear regression - Ordinary least squares

3. Linear regression - geometrical interpretation, numerical issues

4. Ridge regression, bias-variance trade-off

5. Classification setup, Decision trees

6. Ensemble methods (Random forests, Adaboost)

7. K-nearest neighbors for classification and regression

8. Logistic regression

9. Model evaluation, cross-validation

10. Feature selection

11. Unsupervised learning setup, Association rules

12. Hierarchical clustering, the k-means algorithm

Cíle studia:

The course aims to introduce students to a rapidly developing field of machine learning.

Studijní materiály:

1. Deisenroth M. P. : Mathematics for Machine Learning. Cambridge University Press, 2020. ISBN 978-1108455145.

2. Alpaydin E. : Introduction to Machine Learning. MIT Press, 2020. ISBN 978-0262043793.

3. Murphy K. P. : Machine Learning: A Probabilistic Perspective. MIT Press, 2012. ISBN 978-0-262-01802-9.

4. Bishop Ch. M. : Pattern Recognition and Machine Learning. Springer, 2006. ISBN 978-0387-31073-2.

5. Hastie T., Tibshirani R., Friedman J. : The Elements of Statistical Learning. Springer, 2009. ISBN 978-0-387-84857-0.

Poznámka:

All informations and course materials can be fond at https://courses.fit.cvut.cz/BIE-ML1/

Další informace:

https://courses.fit.cvut.cz/BIE-ML1/

Rozvrh na zimní semestr 2023/2024:

	06:00–08:0008:00–10:0010:00–12:0012:00–14:0014:00–16:0016:00–18:0018:00–20:0020:00–22:0022:00–24:00
Po
Út	místnost T9:346 Da Silva Alves R. 09:15–10:45 (přednášková par. 1) Dejvice NBFIT učebnamístnost T9:303 Da Silva Alves R. 11:00–12:30 (přednášková par. 1 paralelka 101) Dejvice NBFIT PC ucebna
St
Čt
Pá

Rozvrh na letní semestr 2023/2024:

Rozvrh není připraven

Předmět je součástí následujících studijních plánů:

• Bachelor specialization, Computer Science, 2021 (povinně volitelný předmět)