{"id":1916,"date":"2024-07-25T18:37:18","date_gmt":"2024-07-25T15:37:18","guid":{"rendered":"https:\/\/www.iem.ihu.gr\/?post_type=course&p=1916"},"modified":"2026-01-14T17:35:09","modified_gmt":"2026-01-14T15:35:09","slug":"95-05","status":"publish","type":"course","link":"https:\/\/www.iem.ihu.gr\/en\/courses\/95-05\/","title":{"rendered":"Intelligent Systems"},"author":5,"template":"","meta":{"_acf_changed":false},"semester":[67],"course_type":[59],"class_list":["post-1916","course","type-course","status-publish","hentry","semester--1-2-3-9","course_type-optional"],"acf":{"code":"95.05","semester":67,"level":"1","teaching_activities":{"activity_1":{"description":"Theory","weekly_hrs":2,"ects":4},"activity_2":{"description":"Lab","weekly_hrs":1,"ects":""},"activity_3":{"description":"","weekly_hrs":"","ects":""},"activity_4":{"description":"","weekly_hrs":"","ects":""},"activity_5":{"description":"","weekly_hrs":"","ects":""}},"type":59,"language":"\u0395\u03bb\u03bb\u03b7\u03bd\u03b9\u03ba\u03ac","erasmus":"\u038c\u03c7\u03b9","url":"https:\/\/exams-sm.the.ihu.gr\/enrol\/index.php?id=57","prerequisites":"","instructors":"","coordinator":"","content":"\u2022 Introduction to Intelligent systems\r\n\u2022 Fuzzy Logic - Fuzzy Sets\r\n\u2022 Participation Functions, Mathematical Representation\r\n\u2022 Transactions between Fuzzy Sets (application of operators)\r\n\u2022 Relationships between Fuzzy Sets, Fuzzy Inference\r\n\u2022 Export rules (clustering, k-means algorithm)\r\n\u2022 Fuzzy Conclusion (modus ponens, Synthetic Rule of Conclusion)\r\n\u2022 Artificial Neural Networks\r\n\u2022 Perceptron, Convergence Theorem\r\n\u2022 Linear Neural Networks\r\n\u2022 Feedforward networks\r\n\u2022 Backpropagation learning algorithm\r\n\u2022 Deep learning\r\n\u2022 Matlab Software \/ Matlab Toolbox","goals":"The aim of the course is to teach students both the necessary theoretical knowledge of intelligent systems as well as allow them to get familiar with practical laboratory tools.\r\nUpon successful completion of the course students will:\r\n- have knowledge of the basic concepts in the field of intelligent systems\r\n- be able to apply knowledge in practice, search, analyze and synthesize data and information using the necessary technologies\r\n- define, analyze and describe the development of an intelligent system in one or more applications that have been taught\r\n-distinguish the characteristics of a problem which will lead them to its successful modelling\r\n- produce solutions based on techniques of fuzzy systems and neural networks\r\n- be able to follow the basic principles of systems development with the technologies that have been taught to compose and propose appropriate applications.","skills":"Research, analysis and synthesis of data and information\r\nUsing corresponding technologies\r\nSetting objectives\r\nProject design\r\nSetting priorities\r\nDecision making\r\nMonitoring results\r\nAutonomous work\r\nDeveloping new research ideas\r\nAdherence to good practice guidelines","teaching_methods":"Lectures, Exercises, Laboratory, Project assignments, Online guidance, Projected presentations, E-mail communication, Online synchronous and asynchronous teaching platform (moodle), Interactive teaching","students_evaluation":"Assessment Language: English \/ Greek\r\nThe final grade of the course is formed by 70% by the grade of the theoretical part and by 30% by the grade of the laboratory part.\r\n1. The grade of the theoretical part is formed by a written final examination and project.\r\nThe written final examination of the theoretical part may include:\r\nSolving problems of applying the acquired knowledge, Short answer questions, multiple choice questions.\r\n2. The examination of the Laboratory Exercises is carried out with laboratory progress in the middle of the semester and laboratory examinations at the end of the semester.","bib_textbooks":"1. P. Tzionas. Intelligent Control, Tools and Applications. (in Greek)\r\n2. I. Vlachavas, P. Kefalas, N. Vassiliadis, F. Kokkoras, I. Sakellariou. Artificial Intelligence - Third Edition, University of Macedonia Publications, ISBN: 978-960-8396-64-7, 2006\/2011. (in Greek)\r\n3. Diamantaras, K. (2007). Artificial Neural Networks. Athens, Greece","bib_journals":""},"_links":{"self":[{"href":"https:\/\/www.iem.ihu.gr\/en\/wp-json\/wp\/v2\/course\/1916","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.iem.ihu.gr\/en\/wp-json\/wp\/v2\/course"}],"about":[{"href":"https:\/\/www.iem.ihu.gr\/en\/wp-json\/wp\/v2\/types\/course"}],"author":[{"embeddable":true,"href":"https:\/\/www.iem.ihu.gr\/en\/wp-json\/wp\/v2\/users\/5"}],"version-history":[{"count":10,"href":"https:\/\/www.iem.ihu.gr\/en\/wp-json\/wp\/v2\/course\/1916\/revisions"}],"predecessor-version":[{"id":4810,"href":"https:\/\/www.iem.ihu.gr\/en\/wp-json\/wp\/v2\/course\/1916\/revisions\/4810"}],"acf:term":[{"embeddable":true,"taxonomy":"course_type","href":"https:\/\/www.iem.ihu.gr\/en\/wp-json\/wp\/v2\/course_type\/59"},{"embeddable":true,"taxonomy":"semester","href":"https:\/\/www.iem.ihu.gr\/en\/wp-json\/wp\/v2\/semester\/67"}],"wp:attachment":[{"href":"https:\/\/www.iem.ihu.gr\/en\/wp-json\/wp\/v2\/media?parent=1916"}],"wp:term":[{"taxonomy":"semester","embeddable":true,"href":"https:\/\/www.iem.ihu.gr\/en\/wp-json\/wp\/v2\/semester?post=1916"},{"taxonomy":"course_type","embeddable":true,"href":"https:\/\/www.iem.ihu.gr\/en\/wp-json\/wp\/v2\/course_type?post=1916"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}