Direction
INTRODUCTION TO ARTIFICIAL INTELLIGENCE
- GENERAL
-
TEACHING METHODS: TEACHING HOURS (WEEKLY) Lectures
Tutorial
2
1
COURSE TYPE: Specialist Background (Optional) COURSE PREREQUISITES: None TEACHING LANGUAGE: Greek THE COURSE IS OFFERED TO ERASMUS STUDENTS: Yes (English language - by arrangement with the teacher) - LEARNIING RESULTS
-
Course Description and Learning Objectives Upon successful completion of the course, students are expected to have:
Knowledge: to understand the broader scientific field of Artificial Intelligence and the application of its methods in modern business.
Skills: to be able to adopt and apply AI methods in modern business.
Skills: to describe and apply to problems in modern business Knowledge-based Intelligent Systems, Rule-based Intelligent Systems, Fuzzy Systems, Artificial Neural Networks, Evolutionary Algorithms, Hybrid Intelligent Systems, and Knowledge Engineering techniques.
Competencies The course aims to :
- Search, analysis and synthesis of data and information, using the necessary technologies
- Decision making
- Autonomous work
- Group work
- Promotion of free, creative and deductive thinking
- CONTENT
-
The course is a general introduction to the scientific field of Artificial Intelligence and its application in modern business.
Course content:
Search problems
Constraint satisfaction problems
Knowledge-based intelligent systems
Experiential systems,
Fuzzy Systems
Introduction to Artificial Neural Networks
Genetic - Evolutionary Algorithms
Hybrid Intelligent Systems
Knowledge engineering
Data mining and knowledge discovery
- TEACHING and LEARNING METHODS - EVALUATION
-
TEACHING METHOD - Lectures in class
- Face to face - Solving tutorial exercises
Uploading material for further study and solving exercises on the e-class platform
USE OF INFORMATION AND COMMUNICATION TECHNOLOGIES Support for the learning process through the e-class platform METHODS OF INSTRUCTION Method Semester workload Lectures 26 Tutorial - Classroom exercises
Independent solution of exercises
13
39
Independent study 72
Total workload in hours 150 STUDENT LEARNING ASSESMENT The evaluation will be conducted in Greek in three distinct ways:
Written final examination including:
- Three main types of test.
- Comparative evaluation of theory elements
- Problem solving
- RECOMMENDED-BIBLIOGRAPHY
-
1. Negnevitsky Michael, Artificial Intelligence, Edition: 3rd/2017, ISBN: 978-960-418-719-5, A.TZIOLA & S.A. (Book Code in Eudoxos: 59421530)
2.VLACHAVAS I., HEAD P., ΒΑΣΙΛΕΙΑΔΗΣ N., KOKKORAS F., SAKELLARIOU I., TECHNICAL NOHOMOSYNTH - 4th EDITION, 2020, ISBN: 978-618-5196-44-8, Publisher): ASSESSMENT AND ASSET MANAGEMENT COMPANY OF THE UNIVERSITY OF MACEDONIA (Book Code in Eudoxos: 94700120)
3. W. ERTEL INTRODUCTION TO ARTIFICIAL LAW, Edition: 2/2019, ISBN: 9789603307969, Publisher: GRIGORIOS CHRYSOSTOMOU FOUNTAS. (Book Code in Eudoxos: 86053651)
4.Konstantinos Diamantaras, Dimitris Botsis, MECHANICAL LEARNING, Edition: 1/2019, ISBN: 978-960-461-995-5, KLEIDARITHMOS PUBLISHING LTD. (Book Code in Eudoxos: 86198212)
5. Haykin Simon, Neural Networks and Machine Learning, 3rd edition/2010, ISBN: 978-960-7182-64-7, Publisher: A. PAPASOTIRIOU & SIA I.K.E. (Eudox Book Code: 9743)
6.AIKATERINI GEORGULI, Artificial Intelligence, Edition: 1/2016, ISBN: 978-960-603-031-4, Publisher: Hellenic Academic Electronic Textbooks and Aids - Depository "Kallipos" Type: E-book. (Book Code in Eudoxos: 320248)