Course detail
Expert Systems
FSI-VEX Acad. year: 2018/2019 Winter semester
The course deals with the following topics: Architecture and properties of expert systems. Knowledge representation, inference mechanisms. Representing and handling uncertainty. Fuzzy logic, linguistic models, fuzzy expert systems. Tools for building expert systems. Knowledge acquisition, machine learning. Characteristics and demonstrations of selected expert systems. Examples of expert system applications.
Language of instruction
Czech
Number of ECTS credits
5
Supervisor
Department
Learning outcomes of the course unit
Knowledge of basic principles of working and building expert systems. Ability to select and apply a proper tool for building an expert system.
Prerequisites
Mathematical logic, set theory, probability theory, basic knowledge of artificial intelligence.
Planned learning activities and teaching methods
The course is taught through lectures explaining the basic principles and theory of the discipline. Exercises are focused on practical topics presented in lectures.
Assesment methods and criteria linked to learning outcomes
Course-unit credit requirements: active attendance at the seminars, creating simple expert system applications.
Examination: written test (simple problems and theoretical questions), oral exam.
Aims
The goal of the course is to make students familiar with the principles of working expert systems. They will acquire fundamentals of knowledge engineering.
Specification of controlled education, way of implementation and compensation for absences
Attendance at the seminars is required. An absence can be compensated for via solving given problems.
The study programmes with the given course
Programme M2I-P: Mechanical Engineering, Master's
branch M-AIŘ: Applied Computer Science and Control, compulsory
Type of course unit
Lecture
26 hours, optionally
Teacher / Lecturer
Syllabus
1. Introduction to the CLIPS system – facts, templates, rules, patterns, process of inference.
2. Functions in CLIPS, definition of user functions.
3. Characteristic features and structure of expert systems, fields of applications.
4. Rule-based expert systems.
5. Introduction to Prolog.
6. Building expert systems in Prolog.
7. Expert systems based on non-rule and hybrid knowledge representation.
8. Probabilistic approaches to handling uncertainty, Bayesian nets.
9. Handling uncertainty by means of certainty factors and Dempster-Shafer theory.
10. Fuzzy approaches to handling uncertainty.
11. Fuzzy expert systems.
12. Process of building expert system, knowledge engineering.
13. Data mining.
Computer-assisted exercise
26 hours, compulsory
Teacher / Lecturer
Syllabus
1. Introduction to the use of CLIPS system, facts and rules.
2. Templates, solving problems in CLIPS.
3. Defining and using functions in CLIPS.
4. Building expert systems in CLIPS.
5. Introduction to the use of Prolog language.
6. Solving problems in Prolog.
7. Building expert systems in Prolog.
8. Pseudo-bayesian systems.
9. Bayesian networks.
10. Implementation of certainty factors in CLIPS.
11. EXSYS and FLEX systems.
12. LMPS system.
13. Evaluating of semester projects.