Skip to content

Fundamentals Of Artificial Intelligence

Public syllabus for 2025-2026

Academic overview

Programme
AIDC
Period
Year 1, Semester 1
Credits
6
Weeks
14

Curriculum placement

Appears in study plans

Teaching team

Course coordinator
Seminar coordinators
(none)

Learning time distribution

Total
Curriculum Lecture Practice Total Weekly Lecture Practice
42 28 14 3 2 1
Exam hours
6
Individual Study Bibliography study Field study Homework Tutoring Others
108 23 23 50 6 0
Overall
150

Learning outcomes

Knowledge

  • Introduction in Artificial Intelligence

Skills

  • Knowledge of main topics of Artificial Intelligence and specific applications

Responsibility

  • Work in teams and individual projects

Online platform

(none)

Course content

Content Methods Obs
C1. Introduction into artificial intelligence. Intelligent agents. Lecture, exemplification, demonstration 2h, [2] Chapters 1, 2 M.Marin
C2. Solving problems by searching. Uninformed and informed search strategies. Heuristic functions. Lecture, exemplification, demonstration 2h, [2] Chapter 3 M.Marin
C3. Strategies for constraint satisfaction problems. Constraint propagation. Search strategies (intelligent backtracking, constraint learning) Lecture, exemplification, demonstration 2h, [2] Chapter 5 M.Marin
C4-5.Logical agents and inference in first order logic Lecture, exemplification, demonstration 2h [2] Chapters 8, 9 M.Marin
C6. Strategies for optimization problems. Deterministic strategies (hill-climbing). Stochastic strategies (simulated annealing, evolutionary algorithms) Lecture, exemplification, demonstration 2h, [2] Chapter 4 D. Zaharie
C7. Probabilistic reasoning. Probability theory reminder. Naïve Bayes models. Bayesian networks. Lecture, exemplification, demonstration 2h, [2] Chapter 12,13 D. Zaharie
C8. Supervised learning models (regression and classification) and gradient descent. Neural networks and the backpropagation algorithm. Lecture, exemplification, demonstration 2h D. Onchis
C9. Introduction to unsupervised learning (clustering, deep unsupervised learning). Lecture, exemplification, demonstration 2h D. Onchis
C10. Markov decision processes, evaluating policies and finding the optimal value with value iteration. Reinforcement learning, Q-learning and SARSA Lecture, exemplification, demonstration 2h D. Onchis
C11. Philosophical Foundations of Artificial Intelligence Lecture, exemplification, demonstration 2h (online) M. Milojevic
C12. AI and Society. Applications in media & fake news, social networks, medicine, autonomous transport systems Lecture, exemplification, demonstration 2h (online) M. Milojevic
C13. Ethics of AI Lecture, exemplification, demonstration 2h (online) M. Milojevic
C14. Recap. Projects presentations Lecture, exemplification, demonstration 2h (online) All professors

Course bibliography

[1] Stuart Russell, „The history and future of AI”, Oxford Review of Economic Policy 37 (3), 509-520, 2021 [2] Stuart Russell, Peter Norvig, „Artificial intelligence: a modern approach”, global edition 4th, Foundations 19, 23, 2021 [3] Tom Mitchell, „Machine Learning”, McGraw-Hill, 1997 [4] Christopher Manning, Hinrich Schuetze, „Foundations of Statistical Natural Language Processing”,; MIT Press, 2009https://cs50.harvard.edu/ai/2020/, https://cs50.harvard.edu/ai/2020/weeks/0/https://stanford-cs221.github.io/spring2022/, https://stanford-cs221.github.io/spring2022/modules/ http://ai.stanford.edu/~nilsson/mlbook.html

Seminar content

Content Methods Obs
L1. Implementation of search-based algorithms Dialog, Problem posing, Implementation 2h M.Marin
L2. CSP solvers & Logic Dialog, Problem posing, Implementation 2h M. Marin
L3. Strategies for optimization problems Dialog, Problem posing, Implementation 2h D..Zaharie
L4. Probabilistic programming Dialog, Problem posing, Implementation 2h D.Zaharie
L5. Implementation from scratch of basic neural networks for classification and regression. Dialog, Problem posing, Implementation 2h D. Onchis
L6. Applications in media & fake news, social networks, medicine, autonomous transport systems. Dialog, Problem posing, Implementation 2h D. Onchis
L7. Reading AI and ethics. Dialog, Problem posing, Implementation 2h (online) M. Milojevic
Bibliography: [1] Stuart Russell, Peter Norvig, „Artificial intelligence: a modern approach”, global edition 4th, Foundations 19, 23, 2021 [2] Tom Mitchell, „Machine Learning”, McGraw-Hill, 1997 [3] François Chollet, „Deep Learning with Python”, November 2017, ISBN 9781617294433 [4] Lab materials: https://darianonchis.wordpress.com/ or Google Classroom [5] http://scikit-learn.org/stable/ [6] https://www.tensorflow.org/ [7] https://keras.io/ [8] https://colab.research.google.com [9] https://www.kaggle.com/ [10] OR-tools https://developers.google.com/optimization/cp/cp_solver [11] https://pypi.org/project/CSP-Solver/ [12] https://www.pymc.io/projects/docs/en/stable/learn.html

Seminar bibliography

The course follows the overall structure of S. Russel and P. Norvig text book on AI which is world-wide adopted by universities. The contents of the course are related but not significantly overlapping with the Machine Learning and Data Mining course. The course is intended to follow the needs of the IT companies active in the field.

Corroboration

(none)

AI tools guidance

(none)

Evaluation and delivery

Activity Criteria Methods Percentage
C
  • Knowledge of main artificial intelligence approaches
  • Project defense: theoretical part and related questions
  • 40.0%
C
  • Applications of selected algorithms
  • Project defense: application part
  • 30.0%
S
  • Usage of specific Artificial Intelligence software
  • Laboratory assignments
  • 30.0%

Performance standards

Knowledge of at least three basic Artificial Intelligence algorithms. Realization of a project. Correct usage of the presented Artificial Intelligence software packages.

Additional info

(none)