1. SylabUZ
2. Wydział Matematyki, Informatyki i Ekonometrii
3. semestr zimowy 2020/2021
4. Computer science and econometrics - drugiego stopnia z tyt. magistra
5. Uczenie maszynowe

Wygeneruj PDF dla tej strony

Uczenie maszynowe - opis przedmiotu

Cel przedmiotu

The assumption of the course is to familiarize students with machine learning algorithms that are currently very widely used in the practical analysis of various types of databases.

The final goal of the course is for the student to acquire the ability to choose appropriate machine learning methods depending on the practical problem posed. The ability to discover patterns, associations and rules hidden in data. Implementation of the selected model, algorithm in order to solve a given research problem.

Additionally, real data analyzes will be performed using one of the two most commonly used by analysts R or Python programs. After this course, the student will have the ability to use specialized program libraries to solve specific problems using machine learning algorithms.

Wymagania wstępne

Zapisz zmiany

Basic knowledge of statistics and probability theory. The ability to analyze statistical data.

Zakres tematyczny

Lecture / Laboratory:

1. Classification of machine learning methods. Supervised and unsupervised learning methods.

2. Data processing. Basic data mining tasks.

3. Data grouping methods: hierarchical grouping, K-medoid method.

4. Association rules.

5. Classification algorithms: decision trees, random forests, artificial neural networks.

6. Statistical classification model - logistic model.

7. Methods for assessing the quality of classification results with and without supervision.

Metody kształcenia

Lectures: traditional or online form.

Laboratory: solving research problems with the use of machine learning algorithms with the use of specialized libraries of the R or Python program. Discussion on possible solutions to the given problems. Teamwork.

Efekty uczenia się i metody weryfikacji osiągania efektów uczenia się

Opis efektu	Symbole efektów	Metody weryfikacji	Forma zajęć

Warunki zaliczenia

1. Checking the level of preparation of students and their activity both in the laboratory and during the lecture.

2. The laboratory grade will be issued on the basis of the test results and / or projects.

3. The evaluation of the course will result from the degree of advancement of the project performed by the student, i.e. the use of machine learning algorithms adequate to the research problems posed, drawing correct conclusions, presenting the graphical results of the analyzes and assessing the quality of the analyzes carried out.

Literatura podstawowa

1. T. Morzy, Eksploracja danych – metody i algorytmy, Wydawnictwo naukowe PWN, Warszawa, 2013.
2. M. Szeliga, Data science i uczenie maszynowe, Wydawnictwo naukowe PWN, Warszawa, 2017.
3. Christopher M. Bishop Pattern Recognition and Machine Learning, Springer, 2007
4. Lantz B., Machine learning with R. PACKT 2013.
5. J. Koronacki, J. Ćwik: Statystyczne systemy uczące się. Wydanie drugie, EXIT, Warszawa, 2007

Literatura uzupełniająca

1. D.T. Larose, Metody i modele eksploracji danych, Wydawnictwo naukowe PWN, Warszawa, 2012.
2. M. Gągolewski, Programowanie w języku R – Analiza danych,  obliczenia, symulacje, Wydawnictwo naukowe PWN, Warszawa, 2016.
3. T. Górecki Podstawy statystyki z przykładami w R BTC Legionowo 2011.

Uwagi

Zmodyfikowane przez dr Magdalena Wojciech (ostatnia modyfikacja: 18-11-2020 23:59)