(27 intermediate revisions by 5 users not shown)
Riadok 8: Riadok 8:
 
<!--[https://sluzby.fmph.uniba.sk/infolist/sk/1-AIN-304_15.html Informačný list predmetu]-->
 
<!--[https://sluzby.fmph.uniba.sk/infolist/sk/1-AIN-304_15.html Informačný list predmetu]-->
  
For exercises, please see [http://list.fmph.uniba.sk LIST].
+
For exercises, project assignments, and lecture slides, please see the course in [https://moodle.uniba.sk/course/view.php?id=3062 moodle].
  
== News ==
 
'''Exam:''' Thursday, 18. 1. 2018 at 9:00. Please sign up.
 
  
<!-- [[#Archív noviniek|Archív noviniek…]] -->
 
  
 
== Course schedule ==
 
== Course schedule ==
Riadok 24: Riadok 21:
 
|-
 
|-
 
|Lecture
 
|Lecture
|Thursday
+
|Tuesday
|11:30
+
|14:00
|M-IV
+
|F1-108
|[[Maria Markosova|Mária Markošová]],  [[Igor Farkas|Igor Farkaš]]
+
|[[Maria Markosova|Mária Markošová]],  [[Lubica Benuskova|Ľubica Beňušková]]
 
|-
 
|-
|Exercises (other students)
+
|Exercises
|Thursday
+
|Monday
|16:30
+
|10:40
|I-23
+
|I-H3
|[[Peter Gergel|Peter Gergeľ]]
+
|[[Stefan Pocos|Štefan Pócoš]], [[Iveta Beckova|Iveta Bečková]]
|-
+
|Exercises (students of m/AIN, m/INF)
+
|Monday (next week)
+
|9:50
+
|H-6
+
|[[Juraj Holas|Juraj Holas]]
+
  
 
|}
 
|}
  
  
== Syllabus ==
+
== Lecture syllabus ==
  
 
{| class="alternative table-responsive"
 
{| class="alternative table-responsive"
Riadok 51: Riadok 42:
 
!References
 
!References
 
|-
 
|-
|28.09.
+
|21.9.
|What is artificial intelligence, agent-robot going around an obstacle, properties and types of agents.
+
|What is artificial intelligence, properties and types of agents. Uninformed search - state space, uninformed search algorithms, DFS, BFS.
|R&N, ch.2
+
|R&N, ch.2-3.4
 
|-
 
|-
|05.10.
+
|28.9.
|Search, state space, tree search, searching agent, uninformed search.
+
|Informed search, A* algorithm, heuristics and their properties.
|R&N,ch.3.1-4
+
|R&N, ch.3.5-3.6
 
|-
 
|-
|12.10.
+
|5.10.
|Informed search, graph search versus tree search, methods of implementation, heuristics and their properties.
+
|Local search, looking for an optimum, hill climbing, genetic algorithm, simulated annealing etc.
|R&N, ch.3.5-6
+
|R&N, ch.4.1
 
|-
 
|-
|19.10.
+
|12.10.
 
|Constraint satisfaction problem: definition, heuristics, methods of solving.  
 
|Constraint satisfaction problem: definition, heuristics, methods of solving.  
 
|R&N, ch.6
 
|R&N, ch.6
 
|-
 
|-
|26.10.
+
|19.10.
|Basics of game theory, minimax algorithm.
+
|Basics of game theory, MiniMax algorithm, Alpha-Beta pruning, ExpectiMiniMax.
 
|R&N, ch.5
 
|R&N, ch.5
 
|-
 
|-
|02.11.
+
|26.10.
|More complex agents: making inferences and learning. Propositional logic, making inferences.
+
|Logical agents: inference in logical knowledge base.
 
|R&N, ch.7
 
|R&N, ch.7
 
|-
 
|-
|09.11.
+
|9.11.
|Learning from examples: supervised learning, perceptron, classification, regression, model selection, generalization.
+
|Logical agents: inference in logical knowledge base.
|R&N, ch.18.1-7
+
|R&N, ch.7
 
|-
 
|-
 
|16.11.
 
|16.11.
|Unsupervised learning in neural networks: Principal component analysis, Self-organizing map.
+
|Supervised learning: linear and non-linear regression, binary perceptron.
|Marsland (2015), ch.6 & 14
+
|R&N, ch.18.1-18.2, 18.6-18.6.3
 
|-
 
|-
 
|23.11.
 
|23.11.
|Probabilistic learning: basic concepts and methods (Bayes formula).
+
|Multi-layer perceptron, idea of error backpropagation.
|R&N, ch.13,20
+
|R&N, ch.18.6.4-18.7.5
 
|-
 
|-
|30.11.
+
|30.12.
|Reinforcement learning, basic concepts, methods of learning.
+
|Applications of multi-layer perceptron: sonar, NetTalk, ALVINN, LeNet.
|R&N, ch.21
+
|[http://cogsci.fmph.uniba.sk/~holas/res/UI-ch6-ANN.pdf  Artificial Neural Networks]
 
|-
 
|-
|07.12.
+
|7.12.
|Fuzzy systems, fuzzy logic and reasoning.
+
|Unsupervised learning: K-means clustering, KNN, Self-organizing map, Principal component analysis.
|Zadeh (2007)
+
|R&N, ch.18.8-18.8.2
 
|-
 
|-
 
|14.12.
 
|14.12.
|Robotics: basic concepts and tasks.
+
|Quo vadis AI? Problems and visions of future AI methods.
|R&N, ch.25
+
|R&N, ch. 26
 
|}
 
|}
  
 
== References ==
 
== References ==
  
* Russell S., Norwig P. (2010). [http://dai.fmph.uniba.sk/courses/ICI/References/russell-norvig.AI-modern-approach.3ed.2010.pdf Artificial Intelligence: A Modern Approach], (3rd ed.), Prentice Hall. Available in the faculty library.
+
 
* Marsland S. (2015). [http://dai.fmph.uniba.sk/courses/ICI/References/marsland.machine-learning.2ed.2015.pdf Machine Learning: An Algorithmic Perspective], (2nd ed.), CRC Press.
+
* Russell S., Norwig P., [http://cogsci.fmph.uniba.sk/~holas/res/AIMA3.pdf Artificial Intelligence: A Modern Approach (3rd ed.)], Prentice Hall, 2010. Ask lecturers for password. Also available in the faculty library. A.k.a. ''AIMA''.<!-- user:uui, password:uui -->
* Zadeh L. (2007). [http://dx.doi.org/10.4249/scholarpedia.1766 Fuzzy logic], Scholarpedia, 3(3):1766.
+
* Návrat P., Bieliková M., Beňušková Ľ. et al., [https://knihy.heureka.sk/umela-inteligencia-pavol-navrat Umelá inteligencia (3. vydanie)], Vydavateľstvo STU, 2015. ([http://cogsci.fmph.uniba.sk/~holas/res/UI-ch6-ANN.pdf ANN chapter])
  
 
== Course grading ==
 
== Course grading ==
  
* Exercises (30%).
+
The course grading consists of four parts:
* Final exam (50%).
+
* Exercises (30%)
* Projects (20%)
+
* Project (20%)
* <b>Overall grading:</b> A (100-91), B (90-81), C (80-71), D (70-61), E (60-51), Fx (50-0).
+
* Final exam (50%)
 +
Throughout the semester, you can gain 30% for exercises and 20% for the project. You have to earn at least half from each of these. If you do not meet minimal condition from the semester, then you cannot pass the exam. The final exam is worth 50% of the total mark.
 +
 
 +
'''Overall grading:''' A (100-91), B (90-81), C (80-71), D (70-61), E (60-51), Fx (50-0).

Verzia zo dňa a času 12:20, 17. september 2021

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 methods of artificial intelligence. The theory is combined with practical exercises.

For exercises, project assignments, and lecture slides, please see the course in moodle.


Course schedule

Type Day Time Room Lecturer
Lecture Tuesday 14:00 F1-108 Mária Markošová, Ľubica Beňušková
Exercises Monday 10:40 I-H3 Štefan Pócoš, Iveta Bečková


Lecture syllabus

Date Topic References
21.9. What is artificial intelligence, properties and types of agents. Uninformed search - state space, uninformed search algorithms, DFS, BFS. R&N, ch.2-3.4
28.9. Informed search, A* algorithm, heuristics and their properties. R&N, ch.3.5-3.6
5.10. Local search, looking for an optimum, hill climbing, genetic algorithm, simulated annealing etc. R&N, ch.4.1
12.10. Constraint satisfaction problem: definition, heuristics, methods of solving. R&N, ch.6
19.10. Basics of game theory, MiniMax algorithm, Alpha-Beta pruning, ExpectiMiniMax. R&N, ch.5
26.10. Logical agents: inference in logical knowledge base. R&N, ch.7
9.11. Logical agents: inference in logical knowledge base. R&N, ch.7
16.11. Supervised learning: linear and non-linear regression, binary perceptron. R&N, ch.18.1-18.2, 18.6-18.6.3
23.11. Multi-layer perceptron, idea of error backpropagation. R&N, ch.18.6.4-18.7.5
30.12. Applications of multi-layer perceptron: sonar, NetTalk, ALVINN, LeNet. Artificial Neural Networks
7.12. Unsupervised learning: K-means clustering, KNN, Self-organizing map, Principal component analysis. R&N, ch.18.8-18.8.2
14.12. Quo vadis AI? Problems and visions of future AI methods. R&N, ch. 26

References

Course grading

The course grading consists of four parts:

  • Exercises (30%)
  • Project (20%)
  • Final exam (50%)

Throughout the semester, you can gain 30% for exercises and 20% for the project. You have to earn at least half from each of these. If you do not meet minimal condition from the semester, then you cannot pass the exam. The final exam is worth 50% of the total mark.

Overall grading: A (100-91), B (90-81), C (80-71), D (70-61), E (60-51), Fx (50-0).