Hlavné menu
  1. DAI
  2. Education
  3. Bachelor program in Applied Informatics
  1. DAI
  2. Education
  3. Courses
  4. Courses for 1-AIN
d (Zaheslovanie aj linku na Marsland ML knihu)
 
(39 intermediate revisions by 3 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, project assignments, and lecture slides, please see [https://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 ==
 
−
''No news yet''
 
  
 
== Course schedule ==
 
== Course schedule ==
Riadok 22: Riadok 21:
 
|-
 
|-
 
|Lecture
 
|Lecture
−
|Thursday
+
|Monday
−
|11:30
+
|16:30
−
|M-X
+
|A
−
|[[Maria Markosova|Mária Markošová]],  [[Lubica Benuskova|Ľubica Beňušková]]
+
|[[Lubica Benuskova|Ľubica Beňušková]]
 
|-
 
|-
−
|Exercises
+
|Exercises (DAV)
 
|Wednesday
 
|Wednesday
 +
|18:10
 +
|I-H3
 +
|[[Stefan Pocos|Štefan Pócoš]], [[Iveta Beckova|Iveta Bečková]], Branislav Zigo
 +
|-
 +
|Exercises (AIN)
 +
|Friday
 
|9:50
 
|9:50
−
|I-H3
+
|I-H6
−
|[[Juraj Holas|Juraj Holas]]
+
|[[Stefan Pocos|Štefan Pócoš]], [[Iveta Beckova|Iveta Bečková]], Branislav Zigo
  
 
|}
 
|}
Riadok 43: Riadok 48:
 
!References
 
!References
 
|-
 
|-
−
|27.09.
+
|23.9.
−
|What is artificial intelligence, properties and types of agents. Uninformed search - state space, uninformed search algorithms, DFS, BFS.
+
|Introduction, basic notions for intelligent agents, reflex agents, reflex agents with a state
−
|R&N, ch.2-3.4
+
|R&N, ch. 2
 
|-
 
|-
−
|04.10.
+
|30.9.
−
|Informed search, A* algorithm, heuristics and their properties.
+
|Search: uninformed, informed, uniform cost, DBS, BFS, A*, Min Max, greedy, alpha-beta, adversarial
−
|R&N, ch.3.5-3.6
+
|R&N, ch. 3.2.2 -3.5.2, ch. 5.1-5.3
 
|-
 
|-
−
|11.10.
+
|7.10.
−
|Constraint satisfaction problem: definition, heuristics, methods of solving.
+
|Constraint Satisfaction Problems (CSP), heuristics, methods of solving
−
|R&N, ch.6
+
|R&N, ch. 6.1 - 6.3.2
 
|-
 
|-
−
|18.10.
+
|14.10.
−
|Local search, looking for an optimum, hill climbing, genetic algorithm, simulated annealing etc.
+
|Logical agents: inference in logical knowledge base
−
|R&N, ch.4.1
+
|R&N, ch. 7.1 - 7.5, 9.3 - 9.4
 
|-
 
|-
−
|25.10.
+
|21.10.
−
|Basics of game theory, MiniMax algorithm, Alpha-Beta pruning, ExpectiMiniMax.
+
|Local and global optimization, hill climbing, GA, simulated annealing
−
|R&N, ch.5
+
|R&N, ch. 4.1 - 4.2
 
|-
 
|-
−
|08.11.
+
|28.10.
−
|Logical agents:  inference in logical knowledge base.
+
|Introduction to probability, reasoning with uncertainty, Bayes' rule
−
|R&N, ch.7
+
|R&N, ch. 13.1 -13.5
 
|-
 
|-
−
|15.11.
+
|4.11.
−
|Supervised learning: linear and non-linear regression, binary perceptron.
+
|Introduction to nature-inspired computing, inductive learning, regression
−
|R&N, ch.18.1-18.2, 18.6-18.6.3
+
|R&N, ch.18.1-18.2, 18.6.1-18.6.2
 
|-
 
|-
−
|22.11.
+
|11.11.
−
|Multi-layer perceptron, idea of error backpropagation.
+
|Single perceptron, delta rule for supervised learning
−
|R&N, ch.18.6.4-18.7.5
+
|R&N, ch.18.6.3-18.6.4
 
|-
 
|-
−
|29.11.
+
|18.11.
−
|Applications of multi-layer perceptron: sonar, NetTalk, ALVINN, LeNet
+
|Multi-layer perceptron, supervised learning by error backpropagation
−
|
+
|R&N, ch.18.7
 
|-
 
|-
−
|06.12.
+
|25.11.
−
|Unsupervised learning: K-means clustering, KNN, Self-organizing map, Principal component analysis
+
|Unsupervised learning: K-means clustering, KNN, Self-organizing map
 
|R&N, ch.18.8-18.8.2
 
|R&N, ch.18.8-18.8.2
 
|-
 
|-
−
|13.12.
+
|2.12.
−
|Weight optimization of MLP using genetic algorithms, evolutionary robotics
+
|Applications of multi-layer perceptron: sonar, NetTalk, ALVINN, LeNet
−
|
+
|[http://cogsci.fmph.uniba.sk/~holas/res/UI-ch6-ANN.pdf  Artificial Neural Networks]
 +
|-
 +
|9.12.
 +
|Evolutionary robotics
 +
|R&N, ch. 25.1.-25.2, 25.7
 
|-
 
|-
−
|20.12.
+
|16.12.
 
|Quo vadis AI? Problems and visions of future AI methods
 
|Quo vadis AI? Problems and visions of future AI methods
 
|R&N, ch. 26
 
|R&N, ch. 26
Riadok 95: Riadok 104:
  
  
−
* Russell S., Norwig P. (2010). [http://cogsci.fmph.uniba.sk/~holas/res/AIMA3.pdf Artificial Intelligence: A Modern Approach], (3rd ed.), Prentice Hall. Ask lecturers for password. Also available in the faculty library. A.k.a. ''AIMA''.<!-- user:uui, password:uui -->
+
* 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. ''R&N''.<!-- user:uui, password:uui -->
−
* Marsland S. (2015). [http://cogsci.fmph.uniba.sk/~holas/res/ML_Marsland.pdf Machine Learning: An Algorithmic Perspective], (2nd ed.), CRC Press. Ask lecturers for password.<!-- user:uui, password:uui -->
+
* Návrat P., Bieliková M., Beňušková Ľ. et al., [https://www.martinus.sk/?uItem=224899 Umelá inteligencia (3. vydanie)], Vydavateľstvo STU, 2015. ([http://cogsci.fmph.uniba.sk/~holas/res/UI-ch6-ANN.pdf ANN chapter])
−
* Zadeh L. (2007). [http://dx.doi.org/10.4249/scholarpedia.1766 Fuzzy logic], Scholarpedia, 3(3):1766.
+
  
 
== Course grading ==
 
== Course grading ==
  
−
The course grading consists of four parts:
+
The course grading consists of three parts:
−
* Exercises (25%)
+
* Exercises (36%)
−
* Short tests (10%)
+
* 5-min exams (10%)
−
* Project (15%)
+
* Project (14%)
−
* Final exam (50%)
+
* Final exam (40%)
−
You have to gain at least half of the points '''from each of these''' in order to pass the course. (E.g. ''10p from excercises'' + full from tests, project, and final exam will still result in Fx.)
+
Throughout the semester, you can gain 36% for exercises, 10% for 5-min exams, and 14% 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 40% of the total mark.
  
 
'''Overall grading:''' A (100-91), B (90-81), C (80-71), D (70-61), E (60-51), Fx (50-0).
 
'''Overall grading:''' A (100-91), B (90-81), C (80-71), D (70-61), E (60-51), Fx (50-0).

Aktuálna revízia z 19:51, 16. september 2024

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 Monday 16:30 A Ľubica Beňušková
Exercises (DAV) Wednesday 18:10 I-H3 Štefan Pócoš, Iveta Bečková, Branislav Zigo
Exercises (AIN) Friday 9:50 I-H6 Štefan Pócoš, Iveta Bečková, Branislav Zigo


Lecture syllabus

Date Topic References
23.9. Introduction, basic notions for intelligent agents, reflex agents, reflex agents with a state R&N, ch. 2
30.9. Search: uninformed, informed, uniform cost, DBS, BFS, A*, Min Max, greedy, alpha-beta, adversarial R&N, ch. 3.2.2 -3.5.2, ch. 5.1-5.3
7.10. Constraint Satisfaction Problems (CSP), heuristics, methods of solving R&N, ch. 6.1 - 6.3.2
14.10. Logical agents: inference in logical knowledge base R&N, ch. 7.1 - 7.5, 9.3 - 9.4
21.10. Local and global optimization, hill climbing, GA, simulated annealing R&N, ch. 4.1 - 4.2
28.10. Introduction to probability, reasoning with uncertainty, Bayes' rule R&N, ch. 13.1 -13.5
4.11. Introduction to nature-inspired computing, inductive learning, regression R&N, ch.18.1-18.2, 18.6.1-18.6.2
11.11. Single perceptron, delta rule for supervised learning R&N, ch.18.6.3-18.6.4
18.11. Multi-layer perceptron, supervised learning by error backpropagation R&N, ch.18.7
25.11. Unsupervised learning: K-means clustering, KNN, Self-organizing map R&N, ch.18.8-18.8.2
2.12. Applications of multi-layer perceptron: sonar, NetTalk, ALVINN, LeNet Artificial Neural Networks
9.12. Evolutionary robotics R&N, ch. 25.1.-25.2, 25.7
16.12. Quo vadis AI? Problems and visions of future AI methods R&N, ch. 26

References

Course grading

The course grading consists of three parts:

  • Exercises (36%)
  • 5-min exams (10%)
  • Project (14%)
  • Final exam (40%)

Throughout the semester, you can gain 36% for exercises, 10% for 5-min exams, and 14% 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 40% of the total mark.

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

Zdroj: „http://dai.fmph.uniba.sk/w?title=Course:Introduction_to_artificial_intelligence&oldid=23324“