(→Syllabus) |
(→Syllabus) |
||

(25 intermediate revisions by 2 users not shown) | |||

Line 1: | Line 1: | ||

{{CourseHeader | {{CourseHeader | ||

− | | code = 2- | + | | code = 2-IKVa-115/18 |

| title = Introduction to Computational Intelligence | | title = Introduction to Computational Intelligence | ||

}} | }} | ||

Line 23: | Line 23: | ||

|- | |- | ||

|Lecture | |Lecture | ||

− | | | + | |Monday |

− | | | + | |9:50 - 11:30 |

− | |I-9 / | + | |I-9 / in room |

|[[Igor Farkas|Igor Farkaš]] | |[[Igor Farkas|Igor Farkaš]] | ||

|- | |- | ||

Line 31: | Line 31: | ||

|Thursday | |Thursday | ||

|13:10 - 14:40 | |13:10 - 14:40 | ||

− | |i-9 / | + | |i-9 / in room |

|[[Kristina Malinovska|Kristína Malinovská]] | |[[Kristina Malinovska|Kristína Malinovská]] | ||

|} | |} | ||

Line 44: | Line 44: | ||

|- | |- | ||

|1. | |1. | ||

− | | | + | |26.09. |

|What is computational intelligence, basic concepts, relation to artificial intelligence. [http://dai.fmph.uniba.sk/courses/ICI/References/ci-def.4x.pdf slides] | |What is computational intelligence, basic concepts, relation to artificial intelligence. [http://dai.fmph.uniba.sk/courses/ICI/References/ci-def.4x.pdf slides] | ||

− | |Craenen & Eiben (2003); [https://en.wikipedia.org/wiki/Computational_intelligence wikipedia]; R&N (2010), chap.1; | + | |Craenen & Eiben (2003); [https://en.wikipedia.org/wiki/Computational_intelligence wikipedia]; R&N (2010), chap.1; |

|- | |- | ||

|2. | |2. | ||

− | | | + | |03.10. |

− | |Taxonomy of artificial agents, nature of environments. [http://dai.fmph.uniba.sk/courses/ICI/References/ci-agents.4x.pdf slides] | + | |Taxonomy of artificial agents, nature of environments. <!--[http://dai.fmph.uniba.sk/courses/ICI/References/ci-agents.4x.pdf slides]--> |

|R&N (2010), chap.2 | |R&N (2010), chap.2 | ||

|- | |- | ||

|3. | |3. | ||

− | | | + | |10.10. |

− | |Inductive learning via observations, decision trees. Model selection. [http://dai.fmph.uniba.sk/courses/ICI/References/ci-learning.4x.pdf slides] | + | |Inductive learning via observations, decision trees. Model selection. <!--[http://dai.fmph.uniba.sk/courses/ICI/References/ci-learning.4x.pdf slides]--> |

|R&N (2010), ch.18.1-3,18.6; Marsland (2015), ch.12 <!--[http://www.r2d3.us/visual-intro-to-machine-learning-part-1/ DT visualization], [https://www.youtube.com/watch?v=LDRbO9a6XPU DT in python], [https://www.youtube.com/watch?v=2s3aJfRr9gE information entropy], [https://www.youtube.com/watch?v=EuBBz3bI-aA bias-variance tradeoff]--> | |R&N (2010), ch.18.1-3,18.6; Marsland (2015), ch.12 <!--[http://www.r2d3.us/visual-intro-to-machine-learning-part-1/ DT visualization], [https://www.youtube.com/watch?v=LDRbO9a6XPU DT in python], [https://www.youtube.com/watch?v=2s3aJfRr9gE information entropy], [https://www.youtube.com/watch?v=EuBBz3bI-aA bias-variance tradeoff]--> | ||

|- | |- | ||

|4. | |4. | ||

− | | | + | |17.10. |

− | |Supervised learning in feedforward neural networks (perceptrons), pattern classification, regression. | + | |Supervised learning in feedforward neural networks (perceptrons), pattern classification, regression. <!-- [http://dai.fmph.uniba.sk/courses/ICI/References/ci-fwdnn.4x.pdf slides]--> |

|R&N (2010), ch.18.2; Marsland (2015), ch.3-4, Engelbrecht (2007), ch.2-3 | |R&N (2010), ch.18.2; Marsland (2015), ch.3-4, Engelbrecht (2007), ch.2-3 | ||

|- | |- | ||

|5. | |5. | ||

− | | | + | |24.10. |

− | |Unsupervised (self-organizing) neural networks: feature extraction, data visualization. [http://dai.fmph.uniba.sk/courses/ICI/References/ci-unsup.4x.pdf slides] | + | |Unsupervised (self-organizing) neural networks: feature extraction, data visualization. <!--[http://dai.fmph.uniba.sk/courses/ICI/References/ci-unsup.4x.pdf slides]--> |

|Marsland (2015), ch.14, Engelbrecht (2007), ch.4 | |Marsland (2015), ch.14, Engelbrecht (2007), ch.4 | ||

+ | |- | ||

+ | |x | ||

+ | |31.10. | ||

+ | |No lecture (holiday) | ||

+ | |on Thursday we have a class (Q&As) | ||

|- | |- | ||

|6. | |6. | ||

− | | | + | |7.11. |

− | |Probability theory. Bayes formula. Naive Bayes classifier. [http://dai.fmph.uniba.sk/courses/ICI/References/ci-prob.4x.pdf slides] | + | |Probability theory. Bayes formula. Naive Bayes classifier. <!--[http://dai.fmph.uniba.sk/courses/ICI/References/ci-prob.4x.pdf slides]--> |

|R&N (2010), ch.13,20.1-2 | |R&N (2010), ch.13,20.1-2 | ||

|- | |- | ||

|7. | |7. | ||

− | | | + | |14.11. |

|Probabilistic learning: MAP, ML. | |Probabilistic learning: MAP, ML. | ||

|Thursday: mid-term test | |Thursday: mid-term test | ||

|- | |- | ||

|8. | |8. | ||

− | | | + | |21.11. |

|Reinforcement learning I: basic principles and learning methods (TD-learning). Prediction problem. <!--[http://dai.fmph.uniba.sk/courses/ICI/References/ci-rl.4x.pdf slides]--> | |Reinforcement learning I: basic principles and learning methods (TD-learning). Prediction problem. <!--[http://dai.fmph.uniba.sk/courses/ICI/References/ci-rl.4x.pdf slides]--> | ||

|R&N (2010), ch.21.1-2. | |R&N (2010), ch.21.1-2. | ||

|- | |- | ||

|9. | |9. | ||

− | | | + | |28.11. |

|Reinforcement learning II (Q, SARSA), actor-critic, control problem, RL for continuous domains. | |Reinforcement learning II (Q, SARSA), actor-critic, control problem, RL for continuous domains. | ||

− | |R&N (2010), ch.21.3-5 | + | |R&N (2010), ch.21.3-5. |

|- | |- | ||

|10. | |10. | ||

− | | | + | |05.12. |

|Evolutionary computation: basic concepts, genetic algorithms. <!--[http://dai.fmph.uniba.sk/courses/ICI/References/ci-evol.4x.pdf slides]--> | |Evolutionary computation: basic concepts, genetic algorithms. <!--[http://dai.fmph.uniba.sk/courses/ICI/References/ci-evol.4x.pdf slides]--> | ||

− | |Engelbrecht (2007), ch.8 | + | |Engelbrecht (2007), ch.8 |

|- | |- | ||

|11. | |11. | ||

− | | | + | |12.12. |

− | |Fuzzy systems, fuzzy logic and reasoning. <!--[http://dai.fmph.uniba.sk/courses/ICI/References/ci-fuzzy.4x.pdf slides]--> | + | |Fuzzy systems, fuzzy logic and reasoning. <!--[http://dai.fmph.uniba.sk/courses/ICI/References/ci-fuzzy.4x.pdf slides]--> |

− | |Engelbrecht (2007), ch.20-21; Zadeh (2007) | + | |Engelbrecht (2007), ch.20-21; Zadeh (2007) |

− | + | <!-- | |

|12. | |12. | ||

− | | | + | |14.12. |

− | |Explainable artificial intelligence (XAI). <!--[http://dai.fmph.uniba.sk/courses/ICI/References/ci-xai.4x.pdf slides] | + | |Explainable artificial intelligence (XAI) + Revision of main concepts. <!--[http://dai.fmph.uniba.sk/courses/ICI/References/ci-xai.4x.pdf slides] |

|Barreto Arrieta A. et al. (2020) | |Barreto Arrieta A. et al. (2020) | ||

− | + | --> | |

− | + | ||

− | + | ||

− | + | ||

− | + | ||

|} | |} | ||

− | Note: Dates refer to lectures, seminars will be on day+ | + | Note: Dates refer to lectures, seminars will be on day+3 each week. |

== References == | == References == | ||

− | + | <!-- | |

* Barreto Arrieta A. et al. (2020). [https://doi.org/10.1016/j.inffus.2019.12.012 Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI]. Information Fusion, 58, pp. 82-115. | * Barreto Arrieta A. et al. (2020). [https://doi.org/10.1016/j.inffus.2019.12.012 Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI]. Information Fusion, 58, pp. 82-115. | ||

+ | --> | ||

* Craenen B., Eiben A. (2003): [http://dai.fmph.uniba.sk/courses/ICI/craenen.ci.enc03.pdf Computational Intelligence]. In: Encyclopedia of Life Support Sciences, EOLSS Publishers Co. | * Craenen B., Eiben A. (2003): [http://dai.fmph.uniba.sk/courses/ICI/craenen.ci.enc03.pdf Computational Intelligence]. In: Encyclopedia of Life Support Sciences, EOLSS Publishers Co. | ||

* Engelbrecht A. (2007). [http://dai.fmph.uniba.sk/courses/ICI/engelbrecht.comp-intel-intro.07.pdf Computational Intelligence: An Introduction] (2nd ed.), John Willey & Sons. | * Engelbrecht A. (2007). [http://dai.fmph.uniba.sk/courses/ICI/engelbrecht.comp-intel-intro.07.pdf Computational Intelligence: An Introduction] (2nd ed.), John Willey & Sons. | ||

* 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. | * 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. | * 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. | ||

− | + | <!--* Woergoetter F., Porr B. (2008). [http://www.scholarpedia.org/article/Reinforcement_learning Reinforcement learning], Scholarpedia, 3(3):1448.--> | |

− | * Woergoetter F., Porr B. (2008). [http://www.scholarpedia.org/article/Reinforcement_learning Reinforcement learning], Scholarpedia, 3(3):1448. | + | |

* Zadeh L. (2007). [http://www.scholarpedia.org/article/Fuzzy_logic Fuzzy logic], Scholarpedia, 3(3):1766. | * Zadeh L. (2007). [http://www.scholarpedia.org/article/Fuzzy_logic Fuzzy logic], Scholarpedia, 3(3):1766. | ||

== Course grading == | == Course grading == | ||

− | * Active participation during the lectures/exercises ( | + | * Active participation during the lectures/exercises (25%): 15 for lectures, 10 for exercises. Minimum 1/3 of points required. |

+ | * Homework (10%): weekly homework given and discussed at the exercises, usually solved by hand or via excel sheets (no programming necessary) | ||

* Written mid-term test (30%), covering topics of the first half of the semester. | * Written mid-term test (30%), covering topics of the first half of the semester. | ||

* Final written-oral exam (30%): We will discuss 3 randomly chosen (by a computer) questions that basically correspond to weekly topics during the semester. Minimum of 1/3 of all points required. | * Final written-oral exam (30%): We will discuss 3 randomly chosen (by a computer) questions that basically correspond to weekly topics during the semester. Minimum of 1/3 of all points required. | ||

− | * Small final project (10%) = implementation of a small neural network (using an existing Python library) and writing a short report. Note: even without this, the student can still get maximum points if s/he has performed very actively. Deadline: TBA | + | * Small final project (10%) = implementation of a small neural network (using an existing Python library) and writing a short report. Note: even without this, the student can still get maximum points if s/he has performed very actively. <b>Deadline: TBA</b> |

* <b>Overall grading:</b> A (>90%), B (>80%), C (>70%), D (>60%), E (>50%), Fx (otherwise). | * <b>Overall grading:</b> A (>90%), B (>80%), C (>70%), D (>60%), E (>50%), Fx (otherwise). |

## Latest revision as of 23:00, 27 September 2022

# Introduction to Computational Intelligence 2-IKVa-115/18

## Contents

The course objectives are to make the students familiar with basic principles of various computational methods of data processing that can commonly be called computational intelligence (CI). This includes mainly bottom-up approaches to solutions of (hard) problems based on various heuristics (soft computing), rather than exact approaches of traditional artificial intelligence based on logic (hard computing). Examples of CI are nature-inspired methods (artificial neural networks, evolutionary algorithms, fuzzy systems), as well as probabilistic methods and reinforcement learning. After the course the students will be able to conceptually understand the important terms and algorithms of CI, and choose appropriate method(s) for a given task. The theoretical lectures are combined with the seminar where the important concepts will be discussed and practical examples will be shown.

## Course schedule

Type | Day | Time | Room | Lecturer |
---|---|---|---|---|

Lecture | Monday | 9:50 - 11:30 | I-9 / in room | Igor Farkaš |

Seminar | Thursday | 13:10 - 14:40 | i-9 / in room | Kristína Malinovská |

## Syllabus

# | Date | Topic | References |
---|---|---|---|

1. | 26.09. | What is computational intelligence, basic concepts, relation to artificial intelligence. slides | Craenen & Eiben (2003); wikipedia; R&N (2010), chap.1; |

2. | 03.10. | Taxonomy of artificial agents, nature of environments. | R&N (2010), chap.2 |

3. | 10.10. | Inductive learning via observations, decision trees. Model selection. | R&N (2010), ch.18.1-3,18.6; Marsland (2015), ch.12 |

4. | 17.10. | Supervised learning in feedforward neural networks (perceptrons), pattern classification, regression. | R&N (2010), ch.18.2; Marsland (2015), ch.3-4, Engelbrecht (2007), ch.2-3 |

5. | 24.10. | Unsupervised (self-organizing) neural networks: feature extraction, data visualization. | Marsland (2015), ch.14, Engelbrecht (2007), ch.4 |

x | 31.10. | No lecture (holiday) | on Thursday we have a class (Q&As) |

6. | 7.11. | Probability theory. Bayes formula. Naive Bayes classifier. | R&N (2010), ch.13,20.1-2 |

7. | 14.11. | Probabilistic learning: MAP, ML. | Thursday: mid-term test |

8. | 21.11. | Reinforcement learning I: basic principles and learning methods (TD-learning). Prediction problem. | R&N (2010), ch.21.1-2. |

9. | 28.11. | Reinforcement learning II (Q, SARSA), actor-critic, control problem, RL for continuous domains. | R&N (2010), ch.21.3-5. |

10. | 05.12. | Evolutionary computation: basic concepts, genetic algorithms. | Engelbrecht (2007), ch.8 |

11. | 12.12. | Fuzzy systems, fuzzy logic and reasoning. | Engelbrecht (2007), ch.20-21; Zadeh (2007) |

Note: Dates refer to lectures, seminars will be on day+3 each week.

## References

- Craenen B., Eiben A. (2003): Computational Intelligence. In: Encyclopedia of Life Support Sciences, EOLSS Publishers Co.
- Engelbrecht A. (2007). Computational Intelligence: An Introduction (2nd ed.), John Willey & Sons.
- Russell S., Norwig P. (2010). Artificial Intelligence: A Modern Approach, (3rd ed.), Prentice Hall. Available in the faculty library.
- Marsland S. (2015). Machine Learning: An Algorithmic Perspective, (2nd ed.), CRC Press.
- Zadeh L. (2007). Fuzzy logic, Scholarpedia, 3(3):1766.

## Course grading

- Active participation during the lectures/exercises (25%): 15 for lectures, 10 for exercises. Minimum 1/3 of points required.
- Homework (10%): weekly homework given and discussed at the exercises, usually solved by hand or via excel sheets (no programming necessary)
- Written mid-term test (30%), covering topics of the first half of the semester.
- Final written-oral exam (30%): We will discuss 3 randomly chosen (by a computer) questions that basically correspond to weekly topics during the semester. Minimum of 1/3 of all points required.
- Small final project (10%) = implementation of a small neural network (using an existing Python library) and writing a short report. Note: even without this, the student can still get maximum points if s/he has performed very actively.
**Deadline: TBA** -
**Overall grading:**A (>90%), B (>80%), C (>70%), D (>60%), E (>50%), Fx (otherwise).