|
Lecturer(s)
|
-
Hájek Petr, prof. Ing. Ph.D.
-
Příhodová Kateřina, Ing. Ph.D.
|
|
Course content
|
Introduction to artificial intelligence and computational intelligence. Ambient intelligence and social impact of artificial intelligence. An example of a system with artificial intelligence. Machine learning and neural networks. Simple models of neural networks for classification and prediction. Knowledge representation. State space and its search possibilities. Logical models - propositional logic and first order predicate logic. Logic programming languages. Design of simple knowledge systems. Binary expert systems. Procedural schemes. Design of knowledge base for expert systems.
|
|
Learning activities and teaching methods
|
Monologic (reading, lecture, briefing), Dialogic (discussion, interview, brainstorming), Laboratory work
- Individual project
- 30 hours per semester
- Home preparation for classes
- 28 hours per semester
- Contact teaching
- 52 hours per semester
- Preparation for a credit (assessment)
- 10 hours per semester
- Preparation for an exam
- 30 hours per semester
|
|
Learning outcomes
|
The aim of the course is to acquaint students with basic approaches to artificial and computational intelligence and possibilities of their application in various areas of social life.
A student who has successfully completed the course can: explain what are the goals of artificial and computational intelligence, their social impacts and characterize their historical development; distinguish hard computing and soft computing approaches to artificial and computational intelligence; characterize the structure and principle of learning a neural network and to distinguish supervised and unsupervised learning; characterize the state space and to compare the strategies for its search in terms of completeness and time and memory complexity; describe and distinguish declarative and procedural approaches to knowledge representation; distinguish diagnostic and planning expert systems and characterize the function of their basic components. A student who has successfully completed the course can: design a suitable neural network structure and model and learn this network using preprocessed data using a gradient algorithm; to choose the appropriate representation of knowledge for the given task; design a state graph for the task and search it using uninformed and informed search algorithms; design a knowledge base of a simple knowledge and expert system in a logical programming language; derive knowledge using inference rules of propositional logic and first order predicate logic. The student who has successfully completed the course is able to: make independent and responsible decisions and solve complex problems to simplify tasks; include in the problem-solving consideration the social and ethical dimensions of technological development; acquire additional expertise, skills and competences from related disciplines; communicate effectively with the target group of users - experts in public administration, security and others.
|
|
Prerequisites
|
A student who has successfully completed the course can: explain what are the goals of artificial and computational intelligence, their social impacts and characterize their historical development; distinguish hard computing and soft computing approaches to artificial and computational intelligence; characterize the structure and principle of learning a neural network and distinguish supervised and unsupervised learning; characterize the state space and to compare the strategies for its search in terms of completeness and time and memory complexity; describe and distinguish declarative and procedural approaches to knowledge representation; distinguish diagnostic and planning expert systems and characterize the function of their basic components.
|
|
Assessment methods and criteria
|
Written examination, Home assignment evaluation, Didactic test, Discussion, Class observation
Assignment: participation in exercises (see directive), written tests throughout the semester with a success rate of at least 60 %, completion and successful defence of two projects. The examination is written with a success rate of at least 60 %.
|
|
Recommended literature
|
-
HAGAN, M .T., DEMUTH, H. B., BEALE, M. D., DE JESUS, O. Neural network design. Oklahoma: Martin Hagan, 2014. ISBN 978-0-9717321-1-7.
-
NEGNEVITSKY, M. Artificial intelligence: A guide to intelligent systems. Harlow: Pearson Education, 2011. ISBN 9781408225745.
-
Russell, Stuart J. Artificial intelligence : a modern approach. Harlow: Pearson Education, 2014. ISBN 978-1-292-02420-2.
|