• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site

Machine Learning

2022/2023
Academic Year
ENG
Instruction in English
5
ECTS credits
Course type:
Elective course
When:
3 year, 1, 2 module

Instructor

Course Syllabus

Abstract

Machine Learning belongs to the family of disciplines related to the analysis of real data, based on the application of mathematical statistics, data analysis, pattern recognition, extraction of patterns from data. In this course classical algorithms of machine learning based on tabular, textual data and images are consideredfrom the point of view of applicability of models for sociological analysis. This course is aimed at students with no or minimal programming skills. In this course, students gain an understanding of the possibility of data analysis, structuring digital data formats, methods and tools for statistical, social analysis based on machine learning algorithms.The course is implemented on the basis of the software tool 'Orange data mining' (https://orangedatamining.com/), in which the creation of the research scheme is reduced to visual programming. This course is implemented for two modules. The students' reporting consists of the following. In each module, students must present a small research project (in the form of an oral presentation and research workflow based on the passed material). At the end of the course there will be an exam on all passed material.
Learning Objectives

Learning Objectives

  • Learn algorithms and their main advantages and limitations for social science goals
  • Obtain skills to work with machine learning software / codes
  • Be able to work with different types of data, such as textual/tabular data and images.
Expected Learning Outcomes

Expected Learning Outcomes

  • Analyze data with machine learning tools
  • Do textual preprocessing (lemmatization and tokenization)
  • Present the resulting project in terms of machine learning
  • Visualize results of the analysis
  • Analyze textual, numerical data and images
Course Contents

Course Contents

  • Topics of lectures and seminars: 1 module
  • Topics of lectures and seminars: 2 module
Assessment Elements

Assessment Elements

  • non-blocking Exam
    The exam consists of 3 practical tasks, for which students will have to demonstrate knowledge of machine learning algorithms and the ability to use them in solving practical tasks. The student must present the solution to the problems in the form of a research diagram, performed in the program 'Orange data mining'. The student's work will be evaluated on the basis of the solutions presented in exams.If questions arise from the teacher, the student should explain the operation of the individual parts of the diagrams presented.
  • non-blocking Presentation project
    The presentation project in the first and second modules are a small creative-scientific investigation using machine learning models. The research should be presented in English. The presentation should include the goals and objectives of the project, a description of the models used, and the results obtained (see details in ‘Presentation Requirement’).
Interim Assessment

Interim Assessment

  • 2022/2023 2nd module
    Cumulative evaluation = 0.3*Presentation_project(1 module) + 0.3*Presentation_project(2 module) Final score = cumulative evaluation + 0.4*Exam. The presentation projcet in the first and second modules are a small creative-scientific investigation using machine learning models. The research should be presented in English. The presentation should include the goals and objectives of the project, a description of the models used, and the results obtained (see details in ‘Presentation Requirement’).
Bibliography

Bibliography

Recommended Core Bibliography

  • Miroslav Kubat. (2017). An Introduction to Machine Learning (Vol. 2nd ed. 2017). Springer.

Recommended Additional Bibliography

  • Črt Gorup, Mitar Milutinovič, Matija Polajnar, Marko Toplak, & Lan Umek. (n.d.). Orange: Data Mining Toolbox in Python. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsbas&AN=edsbas.59267479