There are no prerequisites.
Problem solving and search:
review of problem solving techniques, advanced heuristic search techniques, space efficient techniques, real-time search.
robot planning, task planning and scheduling, means-ends planning, partial order planning, planning graphs and GRAPHPLAN.
review of basic methods (Bayes and naive Bayes classifier, learning of trees and rules, handling noise, pruning of trees and rules), MDL principle, Support Vector Machines, evaluating success of learning and comparing learning algorithms, learnability and theoretical limits for learning.
Other paradigms of machine learning:
inductive logic programming, reinforcement learning, constructive learning and discovering new concepts with functional decomposition.
Reasoning with uncertainty:
reasoning and learning in Bayesian networks, construction of networks and causality.
Qualitative reasoning and modelling:
qualitative and quantitative modelling, modelling without numbers, qualitative simulation of dynamic systems.
Genetic algorithms, genetic programming and other problem-solving paradigms.
1) S. Russell, P. Norvig, Artificial Intelligence: A Modern Approach, 3rd edition, Prentice-Hall 2009, ISBN-013:978-0-13-604259-4.
2) I. Witten, E. Frank, M.A. Hall, C. Pal, Data Mining, 4th edition, Morgan Kaufmann, 2016, ISBN: 978-0128042915.
3) I. Bratko, Prolog Programming for Artificial Intelligence, Fourth edition, Pearson Education, Addison-Wesley 2011, ISBN: 0201403757.
In-depth knowledge of methods and techniques of Artificial Intelligence (AI).
Ability of solving complex practical problems with AI methods.
Competence in using methods and tools of AI in research, including projects in other courses and in the final graduation project.
Ability of conducting research in Artificial Intelligence.
After the completion of the course the student will be able to:- Understand advanced search algorithms, and trade-offs between their time and space complexity, and quality of heuristic solutions produced- Understand algorithms for constructing parallel plans, and methods for partial-order planning as constraint satisfaction- Analyse practical questions of search and planning methods when applied to concrete application problems - Understand the framework and methods of reinforcement learning for sequential probabilistic decision making - Understand the logic-based approach to machine learning, and its practical advantages and drawbacks- Understand the principles and algorithms of qualitative modelling, reasoning and simulation- Able to competently combine and apply AI methods in the implementation of applications in industry, robotics, medicine, biology, etc., and in research
Lectures, laboratory work and projects.
Continuing (homework, midterm exams, project work)
Final (written and oral exam)
grading: 5 (fail), 6-10 (pass) (according to the Statute of UL)
Pet najpomembnejših del:
1. I. Bratko, Prolog Programming for Artificial Intelligence, 4th edition, Pearson Education – Addison-Wesley, 2011.
2. M. Možina, J. Žabkar, I. Bratko. Argument based machine learning. Artificial Intelligence. Vol. 171 (2007), no. 10/15, 922-937.
3. M. Luštrek, M. Gams, I. Bratko. Is real-valued minimax pathological?. Artificial Intelligence.Vol. 170 (2006), 620-642.
4. D. Šuc, D. Vladušič, I. Bratko. Qualitatively faithful quantitative prediction. Artificial Intelligence. Vol. 158, (2004) no. 2, str. -214,
5. I. Bratko, S. Muggleton. Applications od inductive logic programming. Commun. ACM, 1995, vol. 38 (1995), no. 11, 65-70.
Celotna bibliografija je dostopna na SICRISu: