Machine Learning Workshop
Informacje ogólne
Kod przedmiotu: | 1120-INSZI-MSA-0667 |
Kod Erasmus / ISCED: | (brak danych) / (brak danych) |
Nazwa przedmiotu: | Machine Learning Workshop |
Jednostka: | Wydział Matematyki i Nauk Informacyjnych |
Grupy: |
Elective courses, Computer Science Przedmioty obieralne, wydz. MiNI PW |
Punkty ECTS i inne: |
4.00
|
Język prowadzenia: | angielski |
Skrócony opis: |
The objective is to revise and synthesize fundamental information acquired from previous courses in mathematics and widely understood computational intelligence, to expand the scope of interest onto machine learning with a particular focus on practical abilities Prerequisites: Mathematics: algebra, calculus, probability theory, statistics, theoretical foundations of computer science: algorithms and data structures, programming |
Pełny opis: |
Lecture: Lectures cover elementary notions and techniques of the machine learning area: 1. Introduction to the course. Basic schemes of data processing. 2. Data preprocessing. Model quality evaluation. Quality of data and its impact on the modeling outcome. 3. Cluster analysis. Elementary algorithms: k-means, hierarchical clustering. 4. Simple classification techniques: kNN, decision trees, Bayesian procedures, kernel methods. 5. Ensemble learning: random trees, bagging, boosting. 6. Regression. 7. Text mining (documents representation, supervised and unsupervised processing methods). Laboratories: Laboratories’ objective is to broaden knowledge of machine learning tech-niques with a focus on practical abilities. The schedule is parallel to the program of lectures: 1. Data preprocessing. 2. Model evaluation. 3. Cluster analysis. 4. Classification. 5. Text mining. Project: Through the semester students will be carrying on a project work assigned by the teacher. It will be individual project work. The task will require application of methods discussed during the lectures. It will be based on a given data set. It will be necessary to conduct exploratory data analysis, select appropriate model, tune its parameters, apply it to the data, evaluate and interpret the results. The assignment will be split into a few stages, whose completion on time will be necessary. Each phase will require a progress report covering current stage of advancement. The final stage is delivered together with a final report summarizing project work. In addition, each student presents the results in form of a spoken presentation in front of the class. |
Literatura: |
1. T. Mitchell, Machine Learning, McGraw Hill, 1997. 2. I. H. Witten, E. Frank, M. A. Hall, Data Mining: Practical Machine Learning Tools and Techniques, Morgan Kauffman, 2011. 3. J. Koronacki, J. Ćwik, Statystyczne systemy uczące się, EXIT, 2005. 4. M. Krzyśko, W. Wołyński, T. Górecki, M. Skorzybut, Systemy uczące się, WNT, 2008. 5. T. Hastie, R. Tibshirani, J. Friedman, The Elements of Statistical Learning, Springer, 2009. 6. C. M. Bishop, Pattern Recognition and Machine Learning, Springer, 2006. 7. R. O. Duda, P. E. Hart, D. G. Stork, Pattern classification, Wiley, 2001. 8. Środowiska: R i RStudio, Python. |
Metody i kryteria oceniania: |
Course grade is obtained from the project work and it consists of: - 40% implementation of the assignment (the solution) - 30% progress reports - 30% final report, including evaluation and interpretation of the results Each phase of the project work has to be completed on time. Delays result in negative points. |
Zajęcia w cyklu "rok akademicki 2018/2019 - sem. letni" (zakończony)
Okres: | 2019-02-18 - 2019-09-30 |
Przejdź do planu
PN WT WYK
ŚR CZ LAB
PRO
PT LAB
PRO
LAB
PRO
LAB
PRO
|
Typ zajęć: |
Laboratorium, 15 godzin
Projekt, 15 godzin
Wykład, 15 godzin
|
|
Koordynatorzy: | Agnieszka Jastrzębska | |
Prowadzący grup: | Władysław Homenda, Agnieszka Jastrzębska | |
Lista studentów: | (nie masz dostępu) | |
Zaliczenie: | Zaliczenie na ocenę |
Właścicielem praw autorskich jest Politechnika Warszawska.