Introduction to Computational Intelligence

Master Programme in Cognitive Science, Comenius University in Bratislava

Lecturer: prof. Igor Farkaš   Assistant: Mgr. Tomáš Kuzma
Semester: Winter 2017-2018    Time and room: Mon 9:00-11:20 I-9

COURSE OBJECTIVES:
The course goal is to make students familiar with basic principles of various computational methods of data processing that can commonly be called computational intelligence (CI). Here belong mainly bottom-up approaches to solutions of (hard) problems based on various heuristics (the so-called soft computing), rather than exact approaches of traditional artificial intelligence based on logic (hard computing). Examples of CI are nature-inspired methods (neural nets, evolutionary algorithms), fuzzy systems, as well as various probabilistic methods under uncertainty (e.g. Bayesian models) and machine learning methods (e.g. reinforcement learning). After the course the students will be able to conceptually understand the important terms and algorithms of CI, such that they would be able to choose appropriate method(s) for a given task. The theoretical introduction will be complemented by practical examples of task solving.

COURSE REQUIREMENTS:
1. Active participation during the semester (max. 14 points).
2. Written mid-term test (max. 12 points).
3. Final written-oral exam (max. 24 points, 3 questions).

EVALUATION: A (50-46), B (45-41), C (40-36), D (35-31), E (30-26), Fx (25-0)

SYLLABUS:

# Date Topic References
1.25.09.
What is computational intelligence, basic concepts, relation to other fields. ♦Craenen & Eiben (2003), wikipedia
♦Russell & Norwig (2003), chap.1
2.02.10.
 Rational agents, taxonomy. Types of environment. ♦Russell & Norwig (2003), chap.2
3.09.10.
Feedforward neural networks (perceptrons), supervised learning, classification, function approximation. ♦Marsland (2009), ch.2-3, ♦Engelbrecht (2007), ch.2-3
4.16.10.
Self-organizing neural networks: feature extraction, data visualization. ♦Marsland (2009), ch.9-10, ♦Engelbrecht (2007), ch.4
5.23.10.
Inductive learning via observations, decision trees. ♦Russell & Norwig (2003), kap.18.1-3,18.6, ♦Marsland (2009), ch.6.1-2
6.30.10.
Statistical learning, probabilistic models. ♦Russell & Norwig (2003), ch.13,20.1-2, ♦Marsland (2009), ch.8.1-2
7.06.11.
mid-term exam ♦your mind :-)
8.13.11.
Reinforcement learning I: basic principles and learning methods (TD-learning). Prediction problem. ♦Russell & Norvig (2003), ch.17.1-4.
9.20.11.
Reinforcement learning II (Q, SARSA), actor-critic, control problem, RL for continuous domain. ♦Russell and Norvig (2003), ch.21.1-6.
10.27.11.
Evolutionary computation: basic concepts, genetic algorithms. ♦Engelbrecht (2007), ch.8
11.04.12.
Fuzzy systems, fuzzy logic and reasoning. ♦Engelbrecht (2007), ch.20-21, ♦Scholarpedia: Zadeh (2007)

• 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. (2003). Artificial Intelligence: A Modern Approach, (2nd ed.), Prentice Hall. Available in faculty library. The slides of chapters are here.
• Marsland S. (2009). Machine Learning: An Algorithmic Perspective, CRC Press. Available in faculty library.
• Zadeh L. (2007). Fuzzy logic, Scholarpedia, 3(3):1766.