Introduction to Computational Intelligence 2-IKV-115
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 introduction is combined with practical examples.
Course schedule
Type | Day | Time | Room | Lecturer |
---|---|---|---|---|
Lecture | Monday | 9:00 | I-9 | Igor Farkaš |
Practical demonstrations | Monday | 10:30 | I-9 | Tomáš Kuzma |
Syllabus
Date | Topic | References |
---|---|---|
25.09. | What is computational intelligence, basic concepts, relation to artificial intelligence. slides | Craenen & Eiben (2003); wikipedia; R&N (2010), chap.1 |
02.10. | Taxonomy of artificial agents, nature of environments. | R&N (2010), chap.2 |
09.10. | Inductive learning via observations, decision trees. Model selection. | R&N (2010), ch.18.1-3,18.6; Marsland (2009), ch.6.1-2 |
16.10. | Supervised learning in feedforward neural networks (perceptrons), pattern classification, function approximation. | R&N (2010), ch.18.2; Marsland (2009), ch.2-3, Engelbrecht (2007), ch.2-3 |
23.10. | Unsupervised (self-organizing) neural networks: feature extraction, data visualization. | Marsland (2009), ch.9-10, Engelbrecht (2007), ch.4 |
30.10. | mid-term exam | your mind :-) |
06.11. | Statistical learning, probabilistic models. | R&N (2010), ch.13,20.1-2; Marsland (2009), ch.8.1-2 |
13.11. | Reinforcement learning I: basic principles and learning methods (TD-learning). Prediction problem. | R&N (2010), ch.21.1-2. |
20.11. | Reinforcement learning II (Q, SARSA), actor-critic, control problem, RL for continuous domains. | R&N (2010), ch.21.3-5. |
27.11. | Evolutionary computation: basic concepts, genetic algorithms. | Engelbrecht (2007), ch.8 |
04.12. | Fuzzy systems, fuzzy logic and reasoning. | Engelbrecht (2007), ch.20-21, Scholarpedia: Zadeh (2007) |
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. Available in faculty library.
- Russell S., Norwig P. (2010). Artificial Intelligence: A Modern Approach, (3rd ed.). Available in the faculty library.
- Marsland S. (2009). Machine Learning: An Algorithmic Perspective, CRC Press. Available in the faculty library.
- Zadeh L. (2007). Fuzzy logic, Scholarpedia, 3(3):1766.
Course grading
- Active participation during the semester (max. 14 points).
- Written mid-term test (max. 12 points).
- Final written-oral exam (max. 24 points, 3 questions).
- Overall grading: A (50-46), B (45-41), C (40-36), D (35-31), E (30-26), Fx (25-0).