Czech

Not applicable.

Course graduate should be able to:
- explain the differences between the concepts of data, information and knowledge,
- explain the architecture and functionality of expert systems,
- create a base of knowledge for expert system NPS32,
- choose the field of application of expert systems,
- explain the paradigm of multilayer neural networks with backpropagation learning,
- discuss the settings for a parameter, the neural network,
- apply features multi-layered neural network backpropagation learning,
- design own solution of optimization task based on genetic algorithms,
- explain and use analysis of an object, formulation of innovative tasks to be solved, formulation of inventive tasks and use recommendation how to find new solutions,
- apply optical information in technical equipment.

The subject knowledge on the secondary school level is required.

Not applicable.

Techning methods include lectures and computer laboratories. Students have to write a single project during the course.

Condition of petting full credit is absolut (100%) attendance in obligatory parts of lessons - the computer exercises. Students are tested continuously and i tis possible to get maximum 20 points. The final written exam is rated by 70 points at maximum and the oral exam is rated by 10 points at maximum.

1. Modern means in automation - relevance, resources, engineering cybernetics.
2. Data, information, knowledge - definition, examples.
3. Expert systems - definitiv, architectural engeneering, theoretical sources, characteristics, inference engine, creation of knowledge base, acguirement of knowledges, proces sof consultation, aplications.
4. Artificial neural networks - definition, neuron, topology, paradigm, multilayer neural network, backpropagation algorithm, activation, characteristics.
5. Theory of Inventive Problem Solving - analysis of the object to be improved and formulation of innovative task to be solved, then solving of inventive tasks supported by expert system and information from world patent databases.
6. Computer vision - preprocessing, image segmentation, description, classification.

Not applicable.

The aim of the course is to acquaint the students with modern methods and means in automation. To get knowledge and experience of pattern recognition and using neural networks, expert systems in automation.

The computer exercises are compulsory, the properly excused missed computer exercises can be compensate.

Not applicable.

Not applicable.

Berka P. a kol.: Expertní systémy. Skripta, VŠE Praha, 1998. (CS)
Hlaváč V.- Šonka M.: Počítačové vidění. Grada 1992,Praha,ISBN 80-85424-67-3 (CS)
Mařík V.-Štěpánková O.-Lažanský J.:Umělá inteligence 1. ACADEMIA 1993,Praha,ISBN 80-200-0496-3 (CS)
Mařík V.-Štěpánková O.-Lažanský J.:Umělá inteligence 2. ACADEMIA 1997,Praha,ISBN 80-200-0504-8 (CS)
Šíma J., Neruda R.: Teoretické otázky neuronových sítí. Matfyzpress, Praha 1996 (CS)

Kasabov,N.K.: Foundations of Neural Networks, Fuzzy systems and Knowledge Engineering.The MIT Press,1996,ISBN 0-262-11212-4 (EN)
Schalkoff,R.J.:Artificial Neural Networks. The MIT Press,1997,ISBN 0-07-115554-6 (EN)
Sonka M., Hlavac V., Boyle R.: Image Processing, Analysis and Machine Vision. Thomson, 2008, ISBN 978-0-495-08252-1 (EN)