Line 50: Line 50:
 
|28.09.
 
|28.09.
 
|What is artificial intelligence, agent-robot going around an obstacle, properties and types of agents.
 
|What is artificial intelligence, agent-robot going around an obstacle, properties and types of agents.
|todo R&N, chap.X
+
|R&N, chap.X
 
|-
 
|-
 
|05.10.
 
|05.10.
 
|Search, state space, tree search, searching agent, uninformed search.
 
|Search, state space, tree search, searching agent, uninformed search.
|todo
+
|R&N,ch.X
 
|-
 
|-
 
|12.10.
 
|12.10.
 
|informed search, graph search versus tree search, methods of implementation, heuristics and their properties.
 
|informed search, graph search versus tree search, methods of implementation, heuristics and their properties.
|R&N (2010), todo
+
|R&N, ch.X
 
|-
 
|-
 
|19.10.
 
|19.10.
 
|Constraint satisfaction problem: definition, heuristics, methods of solving.  
 
|Constraint satisfaction problem: definition, heuristics, methods of solving.  
|R&N (2010), ch.X
+
|R&N, ch.6
 
|-
 
|-
 
|26.10.
 
|26.10.
 
|Basics of game theory, minimax algorithm.
 
|Basics of game theory, minimax algorithm.
|todo
+
|R&N, ch.X
 
|-
 
|-
 
|02.11.
 
|02.11.
 
|More complex agents: making inferences and learning. Propositional logic, making inferences.
 
|More complex agents: making inferences and learning. Propositional logic, making inferences.
|todo
+
|R&N, ch.X
 
|-
 
|-
 
|09.11.
 
|09.11.
Line 86: Line 86:
 
|30.11.
 
|30.11.
 
|Reinforcement learning, basic concepts, methods of learning.
 
|Reinforcement learning, basic concepts, methods of learning.
|R&N, ch.21.3-5.
+
|R&N, ch.21
 
|-
 
|-
 
|07.12.
 
|07.12.

Revision as of 17:11, 27 September 2017

Introduction to Artificial Intelligence 1-AIN-304

The course objectives are to provide the students with basic insight into artificial intelligence, that can further be extended in the master programmes. The course covers the basics of symbolic and nature-inspired artificial intelligence. The theory is combined with practical exercises.


Course schedule

Type Day Time Room Lecturer
Lecture Thursday 11:30 M-IV Mária Markošová, Igor Farkaš
Exercises (students of mIKV) Thursday 16:30 H-6 Peter Gergeľ
Exercises (other students) Monday (next week) 9:50 H-6 Juraj Holas


Syllabus

Date Topic References
28.09. What is artificial intelligence, agent-robot going around an obstacle, properties and types of agents. R&N, chap.X
05.10. Search, state space, tree search, searching agent, uninformed search. R&N,ch.X
12.10. informed search, graph search versus tree search, methods of implementation, heuristics and their properties. R&N, ch.X
19.10. Constraint satisfaction problem: definition, heuristics, methods of solving. R&N, ch.6
26.10. Basics of game theory, minimax algorithm. R&N, ch.X
02.11. More complex agents: making inferences and learning. Propositional logic, making inferences. R&N, ch.X
09.11. Learning from examples: supervised learning, perceptron, classification, regression, model selection, generalization, regularization. R&N, ch.18.x
16.11. Nonparametric models, methods of nearest neighobors, finding nearest neighbors with k-d trees, regression. R&N, ch.18.y
23.11. Probabilistic computation: basic concepts and methods (Bayes formula). R&N, ch.13,20
30.11. Reinforcement learning, basic concepts, methods of learning. R&N, ch.21
07.12. Fuzzy systems, fuzzy logic and reasoning. Zadeh (2007)
07.12. Robotics: basic concepts and tasks. R&N (2010), ch.25

References

Course grading

  • Exercises (30%).
  • Final exam (50%).
  • Projects (20%)
  • Overall grading: A (50-46), B (45-41), C (40-36), D (35-31), E (30-26), Fx (25-0).