# FI:PV021 Neural Networks - Course Information

## PV021 Neural Networks

**Faculty of Informatics**

Spring 2009

**Extent and Intensity**- 2/2. 4 credit(s) (plus extra credits for completion). Type of Completion: zk (examination).
**Teacher(s)**- doc. RNDr. Jiří Šíma, DrSc. (lecturer), prof. RNDr. Mojmír Křetínský, CSc. (deputy)

doc. RNDr. Jan Bouda, Ph.D. (assistant)

Lukáš Mojžiš (assistant) **Guaranteed by**- prof. RNDr. Mojmír Křetínský, CSc.

Department of Computer Science – Faculty of Informatics

Contact Person: prof. RNDr. Mojmír Křetínský, CSc. **Timetable**- Thu 19. 3. 10:00–19:50 B003, Fri 20. 3. 8:00–16:50 B003, Thu 23. 4. 10:00–19:50 B003, Fri 24. 4. 8:00–16:50 C525, Thu 14. 5. 10:00–19:50 B003
**Prerequisites**- Recommended: knowledge corresponding to the courses MB000 (Calculus I) and MB003 (Linear Algebra and Geometry I) or to the courses MB102 (Mathematics II) and MB103 (Mathematics III)
**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 37 fields of study the course is directly associated with, display
**Course objectives**- The goal of this course is to begin to understand the foundations of computation performed via Neural Networks. We will concentrate on an Introduction to Neural Networks: motivations, position of neural networks in computer science, review of basic standard models.
**Syllabus**- Introduction to Neural Networks. History of neurocomputing; neurophysiological motivations; mathematical model of neural network: formal neuron, organizational, active, and adaptive dynamics; position of neural networks in computer science: comparison with von Neumann computer architecture, applications, implementations, neurocomputers.
- Classical Models of Neural Networks. Perceptron: convergence; multi-layered network and backpropagation strategy: choice of topology and generalization; MADALINE: Widrow learning rule.
- Associative Neural Networks. Linear associative network: Hebb law and pseudohebbian adaptation; Hopfield network: energy, capacity; continuous Hopfield network: traveling salesman problem; Boltzmann machine: simulated annealing, equilibrium.
- Self-Organization. Kohonen network: unsupervised learning; Kohonen maps: LVQ; counterpropagation: Grossberg learning rule; RBF networks.
- Seminar: Software implementation of particular neural network models and their simple applications.

**Literature**- ŠÍMA, Jiří and Roman NERUDA.
*Teoretické otázky neuronových sítí*. Vyd. 1. Praha: Matfyzpress, 1996, 390 s. ISBN 80-85863-18-9. info - KOHONEN, Teuvo.
*Self-Organizing Maps*. Berlin: Springer-Verlag, 1995, 392 pp. Springer Series in Information Sciences 30. ISBN 3-540-58600-8. info - HAYKIN, Simon S.
*Neural Networks : a comprehensive foundation*. New York: Macmillan College Publishing Company, 1994, xix, 696. ISBN 0023527617. info *Sofsem '88 : sborník referátů : Zotavovna ROH Petr Bezruč, Malenovice, Beskydy 27.11.-9.12.1988*. Brno: Ústav výpočetní techniky UJEP Brno, 1988, 363 s. info

- ŠÍMA, Jiří and Roman NERUDA.
**Assessment methods**- Lectures, class discussion, group projects (4 to 6 people per project). Several midterm progress reports on the respective projects, one final project presentation plus oral examination.
**Language of instruction**- Czech
**Further comments (probably available only in Czech)**- The course is taught once in two years.

General note: v semestru jaro 2006 se nekona. **Listed among pre-requisites of other courses**

- Enrolment Statistics (Spring 2009, recent)
- Permalink: https://is.muni.cz/course/fi/spring2009/PV021