Navigation

22MOIS - Intelligent Systems Fundamentals

Course specification
Course titleIntelligent Systems Fundamentals
Acronym22MOIS
Study programme
Module
Lecturer (for classes)
Lecturer/Associate (for practice)
    Lecturer/Associate (for OTC)
      ESPB4.0Status
      ConditionNoneОблик условљености
      The goalThe goal of the Intelligent Systems Fundamentals course is for students to achieve basic knowledge of intelligent systems, their application, different methods of implementing systems with "intelligent" functionalities, as well as the development of skills necessary to design and implement intelligent systems in process engineering.
      The outcomeAfter completing and passing the exam, students will be able to apply fundamental intelligent system techniques in problem solving, knowledge representation, reasoning and learning, and they will be able to understand and apply different artificial intelligence and machine learning techniques in modelling and process regulation.
      Contents
      Contents of lecturesIntelligent systems fundamentals. Search algorithms. Data classification and estimation of correlation in data. Machine learning. Nearest neighbor methods. Logical programming. Neural networks. Genetic algorithms.
      Contents of exercisesPractical lessons are carried out in the computer lab. Application of artificial intelligence and machine learning techniques through the use of software tools and programming languages (Python, etc.) in process engineering examples. The students will also be given assigments to carry out on their own.
      Literature
      1. Material from the lectures and practical exercises
      2. "Artificial Intelligence: A Modern Approach", S. Russell, P. Norvig, Prentice Hall, 2009
      3. "Artificial Intelligence with Python: A Comprehensive Guide to Building Intelligent Apps for Python Beginners and Developers", P. Joshi, Packt, 2017
      4. "Mašinsko učenje", O. Joldžić, D. Kosić, Akademska misao, 2020 (Original title)
      5. "Introduction to Machine Learning", fourth edition, E. Aplaydin, The MIT Press, 2020 (Original title)
      Number of hours per week during the semester/trimester/year
      LecturesExercisesOTCStudy and ResearchOther classes
      22
      Methods of teachingLectures, practical classes in the computer laboratory, consultations
      Knowledge score (maximum points 100)
      Pre obligationsPointsFinal examPoints
      Activites during lecturesTest paper30
      Practical lessonsOral examination
      Projects
      Colloquia
      Seminars20