Skip to main content

Intelligent Systems

2026/2027
Programme:
Interdisciplinary University Study Programme Computer Science and Mathematics
Year:
3 year
Semester:
first
Kind:
optional
ECTS:
6
Language:
english
Course director:

Marko Robnik Šikonja

Hours per week – 1. semester:
Lectures
3
Seminar
0.4
Tutorial
1.6
Lab
0
Prerequisites

Knowledge of basic statistics and programming.

Content (Syllabus outline)

Lecture topics:

  1. Introduction to intelligent systems and data science
  2. Nature inspired computing (genetic algorithms, genetic programming)
  3. Introduction to predictive modelling
  4. Bias, variance and overfitting
  5. Representation learning and feature selection
  6. Ensemble methods
  7. Kernel methods
  8. Neural networks: architectures, backpropagation, deep neural networks
  9. Model inference and explanation
  10. Natural language processing: text representation, information extraction, text classification, semantic similarity
  11. Reinforcement learning: basic approaches and algorithms, Q learning, TD learning, deep RL
Readings

G. James, D. Witten, T. Hastie, and R. Tibshirani, 2021. An introduction to statistical learning with applications in R, 2nd edition. New York: Springer.

D. Jurafsky, J. H. Martin. Speech and language processing: An introduction to natural language processing, computational linguistics, and speech recognition. 3rd edition draft, 2022

Richard S. Sutton and Andrew G. Barto: Reinforcement Learning, An Introduction, 2nd edition, MIT press, 2018

Objectives and competences

The goal of the course is the students to become acquainted with the field of intelligent systems, which includes a collection of tools and approaches for solving problems which are difficult or unpractical to tackle with other methods. Students will be able to apply the gained theoretical knowledge on real-world problems from scientific and business environment. The students shall be able to decide which of the presented techniques should be used for a given problem, and to develop a prototype solution.

 

General competences:

  • the ability to understand and solve professional challenges in computer and information science,

  • the ability of professional communication in the native language as well as a foreign language,

  • the ability to apply acquired knowledge in independent work for solving technical and scientific problems in computer and information science,

  • familiarity with research methods in the field of computer science.

 

Subject-specific competences:

  • using basic machine learning algorithms

  • preprocessing data for data mining

  • feature subset selection

  • evaluation of decision models

  • using data mining systems

  • using optimizations packages with evolutionary techniques

  • text analysis and text mining

  • using reinforcement learning tools

Intended learning outcomes

Upon course completion the student will:

  • know and use various techniques and methods for modelling of intelligent systems
  • know and use machine learning tools
  • know and use text analysis approaches
  • solve and analyse examples of intelligent systems using scientific methods
  • use and evaluate tools for statistical modelling and data mining
  • be capable to analyse problems from the area of intelligent systems and choose adequate approaches for their solutions
  • use and compare different approaches for evolutionary computing
Learning and teaching methods

Lectures, assignments with written and oral demonstrations and presentations, seminar works and homework. Students from small project teams and autonomously solve assignments based on real-life problems. The teams describe their solutions in written reports and prepare short oral presentations. Written reports and oral presentations are graded.

Assessment

Type: written and oral exam, coursework, project.

Continuing: homework, project work.
Final: written and oral exam.
Grading: 6-10 pass, 5 fail
(according to the rules of University of Ljubljana).

Lecturer's references
  1. VREŠ, Domen, ROBNIK ŠIKONJA, Marko. Preventing deception with explanation methods using focused sampling. Data mining and knowledge discovery. 2023, vol. , no. , str. 1-46
  2. MIOK, Kristian, ŠKRLJ, Blaž, ZAHARIE, Daniela, ROBNIK ŠIKONJA, Marko. To BAN or not to BAN: Bayesian attention networks for reliable hate speech detection. Cognitive computation.  Jan. 2022, vol. 14, iss. 1, str. 353-371
  3. ŠKVORC, Tadej, GANTAR, Polona, ROBNIK ŠIKONJA, Marko. MICE: mining idioms with contextual embeddings. Knowledge-based systems. Jan. 2022, vol. 235, str. 1-11
  4. MARTINC, Matej, POLLAK, Senja, ROBNIK ŠIKONJA, Marko. Supervised and unsupervised neural approaches to text readability. Computational linguistics. 2021, vol. 47, no. 1, str. 141-179
  5. LAVRAČ, Nada, ŠKRLJ, Blaž, ROBNIK ŠIKONJA, Marko. Propositionalization and embeddings: two sides of the same coin. Machine learning. 2020, vol. 109, no. 7, str. 1465-1507.

Celotna bibliografija je dostopna na SICRISu https://cris.cobiss.net/ecris/si/sl/researcher/8741

Complete bibliography is available in SICRIS: https://cris.cobiss.net/ecris/si/en/researcher/8741