Introduction to Artificial Intelligence
- define the basic concepts of artificial intelligence
- distinguish between symbolic and connectivistic approaches to AI
- apply state search algorithms and biologically inspired optimization algorithms on basic problems
- solve basic problems using logic programming
- apply inference algorithms on basic logical problems
- compare among various approaches to representing uncertainty
- assess the applicability of different AI methods on a given AI problem
- apply the basic machine learning algorithms
- review the philosophical aspects of artificial intelligence
Forms of Teaching
Week by Week Schedule
- AI problems and applications; AI definitions and Turing test; Agents and environments.
- State space search problem; Uninformed search (breadth-first, depth-first, depth-first with iterative deepening).
- Heuristics and informed search (hill-climbing, generic best-first); Minimax search and alpha-beta pruning; Constraint satisfaction (backtracking and local search methods); A* search, beam search.
- Logic as a knowledge representation scheme (ontological and epistemological commitments); Formalizing natural language sentences in predicate logic; Resolution rule for propositional logic; Resolution rule for predicate logic.
- Logic-based expert systems; Reduction to logic programming.
- Description logics and ontologies; Semantic networks; Non-monotonic reasoning; Spatial-temporal reasoning.
- Rule-based reasoning; Case-based and model-based reasoning; Planning; Rule-based expert systems.
- Midterm exam.
- Certainty factors; Fuzzy sets and fuzzy logic; Fuzzy logic inference (fuzzy propositions, fuzzy relations, and fuzzy implications); Fuzzy inference engines; fuzzyfication and defuzzyfication.
- Probabilistic frameworks (Bayesian networks, Markov networks); Bayes inference.
- Machine learning tasks and applications; Machine learning approaches and paradigms; Naïve Bayes classifier; Decision trees (ID3, C4;5).
- Environment, reward and value functions; Markov decision processes (MDP); Approximate dynamic programming methods (Q-learning).
- Perceptron (learning paradigms,Hebbian learning, competitive learning, Boltzmann learning); Multilayer perceptron (error-backpropagation learning, credit-assignment problem, backpropagation through time).
- Philosophical issues.
- Final exam.
Computer Science (module)(6. semester)
Computing (study)(6. semester)
Software Engineering and Information Systems (module)Elective Courses (6. semester)
(.), by Russell, Stuart J; Norvig, Peter. Artificial Intelligence: A Modern Approach. Prentice-Hall, Inc., 2003.,
(.), Dalbelo Bašić, Bojana; Šnajder, Jan. Umjetna inteligencija: Zaključivanje uporabom propozicijske i predikatne logike – zbirka zadataka. Zagreb: FER, 2008.,
L3 English Level
4 Laboratory exercises
0 Project laboratory