PV069 Hybrid Systems of Machine Learning

Faculty of Informatics
Spring 2007
Extent and Intensity
2/1. 3 credit(s) (plus extra credits for completion). Recommended Type of Completion: zk (examination). Other types of completion: k (colloquium), z (credit).
Teacher(s)
doc. Ing. Jan Žižka, CSc. (lecturer)
Mgr. Tomáš Hudík (seminar tutor)
Guaranteed by
prof. RNDr. Jiří Hřebíček, CSc.
RECETOX – Faculty of Science
Contact Person: doc. Ing. Jan Žižka, CSc.
Timetable
Thu 16:00–17:50 B411 and each odd Monday 18:00–19:50 B117
Prerequisites (in Czech)
! P069 Hybrid Systems of Machine Learning
Course Enrolment Limitations
The course is also offered to the students of the fields other than those the course is directly associated with.
fields of study / plans the course is directly associated with
there are 17 fields of study the course is directly associated with, display
Course objectives
This subject introduces basic principles of artificial neural networks and their applications from the practical point of view. It focuses on utilization of combined (hybrid) machine learning methods both for applications and automated support of designing learning algorithms by selected machine learning methods.
Syllabus
  • Artificial perceptrons and neural networks. Basic learning algorithms, delta-rule, back propagation of errors. Features of basic neural network models, problems with over-training and network designs.
  • Transformation of decision trees to neural networks, initialization of weigths.
  • Genetic algorithms, their combinations with neural networks, optimalization of weigths.
  • Hybrid neural networks, combination of inputs and weights using t-norms and t-conorms. AND and OR fuzzy neuron. Fuzzy-neural networks. ANFIS and NEFCON architectures. Neuro-fuzzy classifiers. Optimalization of fuzzy sets within IF-THEN rules.
  • Recurrent, Hopfield, and avalanche networks. Other types of networks.
  • Application examples.
Literature
  • MITCHELL, Tom M. Machine learning. Boston: McGraw-Hill, 1997, xv, 414. ISBN 0070428077. info
Assessment methods (in Czech)
Předmět je ukončen písemnou zkouškou. Cvičení je samostatné na základě zadaných úloh (ověření si vlastností probíraných algoritmů pomocí poskytnutých dat a demonstračního software). Cvičení jsou ohodnocena a tvoří část výsledného hodnocení spolu s písemnou zkouškou. Pokud student/ka neodevzdá výsledky žádného cvičení, nemůže předmět řádně ukončit (pouze písemka nestačí); výsledky se odevzdávají elektronicky.
Language of instruction
Czech
Further Comments
Study Materials
The course is also listed under the following terms Spring 2003, Spring 2004, Spring 2006.
  • Enrolment Statistics (recent)
  • Permalink: https://is.muni.cz/course/fi/spring2007/PV069