|
Lecturer(s)
|
-
Nejedlová Dana, Ing. Ph.D.
|
|
Course content
|
Lectures 1. What is artificial intelligence, its history, and practical applications. 2. Representation of facts in state space, heuristics and a search in state space. 3. Alpha-Beta pruning of a state space of board games for two players. 4. First-order predicate calculus. 5. Complexity of algorithms. 6. Dynamic programming. Computation of Minimal Edit Distance with Dynamic Time Warping algorithm. 7. Decision trees and the entropy of information. 8. Bayesian networks. 9. Neural networks: history, logic function representation, linear separability, supervised learning, Perceptron and Delta Rule. 10. Multilayer neural network: solving of linearly unseparable problems using the backpropagation algorithm. 11. Multilayer neural network: possible applications and methods of training. 12. Hopfield network and the Hebb rule for its training. 13. Kohonen self-organizing network: unsupervised learning. 14. Genetic algorithms. Tutorials 1. Design of a fuzzy logic system for the selection of the best match. 2. Representation of problems in state space. 3. Alpha-Beta pruning. 4. Problem solving using Prolog. 5. Formulation of first-order logic predicates. 6. Naive Bayes classifier. 7. Problem representation using the Decision tree. Computation of the entropy of information. 8. Problem representation using the Bayesian network. Computation of probabilities. 9. Vector classification using the Perceptron and the Delta-Rule. 10. Solving the linearly unseparable problems using the multilayer neural net. 11. Classification using the multilayer neural net with the method of training and test data sets. 12. The Hopfield net used for the reconstruction of degraded pattern. Finding the dependencies in data using the Hopfield and Hebb nets. 13. Solving the non-linear principal components analysis and the traveling salesman problem using the Kohonen self-organizing network. Testing of the genetic algorithm. 14. Test.
|
|
Learning activities and teaching methods
|
Monological explanation (lecture, presentation,briefing), Working activities (workshops)
- Class attendance
- 56 hours per semester
|
|
Learning outcomes
|
Students will learn about modern methods of artificial intelligence as tools for decision making and control. The facts about artificial intelligence will be combined with the knowledge of algebra, programming techniques, and economics.
Students obtain knowledge in given course in accordance with requirements and course programme.
|
|
Prerequisites
|
Completion of courses in Algorithms, Mathematics and Statistics
|
|
Assessment methods and criteria
|
Oral exam, Written exam, Practical demonstration of acquired skills, Systematické pozorování studenta, Presentation of student research activity, Written assignment
Active participation in tutorials. Successful passing of theoretical test. Independent creation and defense of a computer program in arbitrary programming language that solves arbitrary problem by the methods of artificial intelligence.
|
|
Recommended literature
|
-
BISHOP, Christopher M. Pattern Recognition and Machine Learning. New York: Springer, 2006. ISBN 978-0387-31073-2.
-
HAYKIN, Simon O. Neural Networks and Learning Machines. Prentice Hall, 2009. ISBN 978-0131471399.
-
HEATON, Jeff. Artificial Intelligence for Humans, Volume 1: Fundamental Algorithms. Heaton Research, Inc., 2013. ISBN 978-1493682225.
-
HEATON, Jeff. Artificial Intelligence for Humans, Volume 2: Nature-Inspired Algorithms. Heaton Research, Inc., 2014. ISBN 978-1499720570.
-
JONES, M. T. Artificial Intelligence : A Systems Approach. Sudbury : Jones and Bartlett Publishers, 2008. ISBN 978-0-7637-7337-3.
-
KRUSE, R., BORGELT, C., KLAWONN, F., MOEWES, C., STEINBRECHER, M., HELD, P. Computational Intelligence: A Methodological Introduction. Springer-Verlag London, 2013. ISBN 978-1-4471-5012-1.
-
MARSLAND, Stephen. Machine Learning: An Algorithmic Perspective. Chapman & Hall/Crc Machine Learning & Pattern Recognition, 2014. ISBN 978-1466583283.
-
Vladimír MAŘÍK, Olga ŠTEPÁNKOVÁ, Jiří LAŽANSKÝ a kolektiv. Umělá inteligence I. - V.díl. Academia Praha, 2007. ISBN 80-200-0502-1.
|