Budapest University of Technology and Economics, Faculty of Electrical Engineering and Informatics

    címtáras azonosítással

    vissza a tantárgylistához   nyomtatható verzió    

    Artificial Intelligence

    A tantárgy neve magyarul / Name of the subject in Hungarian: Mesterséges intelligencia

    Last updated: 2023. szeptember 15.

    Budapest University of Technology and Economics
    Faculty of Electrical Engineering and Informatics
    Software Engineering, BSc
    Course ID Semester Assessment Credit Tantárgyfélév
    VIMIAC10   3/0/0/f 3  
    3. Course coordinator and department Dr. Hullám Gábor István,
    Web page of the course
    4. Instructors Dr. Hullám, Gábor István  associate professor, Department of Measurement and Information Systems, BME
    5. Required knowledge Mathematical logic, probability, basics of computer science
    6. Pre-requisites
    (TargyEredmeny("BMEVISZAA01" , "jegy" , _ ) >= 2 VAGY
    TargyEredmeny("BMEVISZAA04" , "jegy" , _ ) >= 2 VAGY
    TargyEredmeny("BMEVISZA110" , "jegy" , _ ) >= 2 )

    ÉS NEM ( TárgyEredmény( "BMEVIMIA313" , "jegy" , _ ) >= 2
    TárgyEredmény("BMEVIMIA313", "FELVETEL", AktualisFelev()) > 0
    TárgyEredmény( "BMEVIMIAC00" , "jegy" , _ ) >= 2
    TárgyEredmény("BMEVIMIAC00", "FELVETEL", AktualisFelev()) > 0)

    ÉS (Training.Code=("5N-A8") VAGY Training.Code=("5NAA8"))

    VAGY Szak("6N-MA") VAGY Szak("6NAMAR") //KJK AVCE

    A fenti forma a Neptun sajátja, ezen technikai okokból nem változtattunk.

    A kötelező előtanulmányi rend az adott szak honlapján és képzési programjában található.

    7. Objectives, learning outcomes and obtained knowledge The main objective of the course is to provide a brief but demanding introduction to the field of artificial intelligence. The steps of the introduction are (1) the problem of expressing intelligent behaviour by computational models, (2) the analysis and application of formal and heuristic methods of artificial intelligence, (3) methods and problems of practical implementations.

    The course develops the skills that will enable computer science students to become competent:
    - Study the novel use of the computer (using intelligent methods),
    - develop efficient methods for solving computational problems,
    - understand the technological and conceptual limitations of computer science and computing
    - to understand intellectually the central role of algorithms in information systems.

    8. Synopsis 1. Introduction: choice of AI problems, intelligence and fundamental issues, engineering approach, history.

    2. Analysis of a sample problem. How we manage information. What is needed if the task is not trivial but not impossible. Steps of correct abstraction. What do we gain, what do we give up for it? What are the pitfalls of the solution?

    3. Intelligent systems design: agents, components, environments, architecture and program, search space and basic agent types (behaviour), what to expect inside an agent. What does it mean to be intelligent?

    4. Problem solving by search: what are the overall algorithms of intelligent systems, basic mathematical abstractions. How to creatively apply the algorithms we have learned so far to enhance intelligence.

    5. The role of paradigm shifts - problem solving by constraint satisfaction. Problem solving in a multiagent environment - search in a hostile environment.

    6. The basic component of intelligence - knowledge. Formalising knowledge with logic. What does it mean to reason in logic? There are several logics, how do they differ, what do they provide?

    7. Knowledge engineering, logical description of agents, and problem solving by logical inference. Paradigm shift for scaling up.8. Making plans when everything is going well and when nothing is going well.

    9. Intelligence in the real world - incomplete, uncertain and changing knowledge: uncertainty and probability calculation. Probability nets. Inference in probability nets.

    10. Managing temporal knowledge. Rationality and utility. Intelligence as the ability to make rational decisions. Markov decision processes.

    11. The basic mechanism of intelligence - learning. Basic concepts, basic tasks. Decision trees learning. Learning logical hypotheses.

    12. Learning neural networks. Deep neural networks.

    Learning probability nets, kernel machines.

    14. Reinforcement learning. Q-learning. Deep reinforcement learning.

    15. Recommender systems.

    16. Problems of multi-agent systems.


    9. Method of instruction Lectures and home work on specific topics based on given readings and demo platforms.
    10. Assessment Two large midterm-test (MTs) at a different time from the lecture, the minimum level required for both MTs is 40-40%. During the semester, a timed homework assignment consisting of several parts, which can be retrieved from an appropriately designed homework server. The schedule for the assignment is available on the assignment page. The semester result will be evaluated on the basis of the sum of the two MTs scores and the score obtained on the homework (MT1 score + MT2 score + homework score).

    The semester signature and the grade other than unsatisfactory is conditional on a minimum of 40% in both MTs and 40% of the semester maximum total score - max(MT1 score)+max(MT2 score)+max(homework scoreMTs).

    11. Recaps

    According to the TVSZ*. Each MT can only be corrected once.


    12. Consultations On request, by appointment.
    13. References, textbooks and resources

    Stuart Russell and Peter Norvig: Artificial Artificial Intelligence in Modern Approaches


    14. Required learning hours and assignment
    Preparation for lectures14
    Preparation for mid-term exam12
    15. Syllabus prepared by Dr. Dobrowiecki, Tadeusz  university professor, Department of Measurement and Information Systems, BME
    Dr. Hullám, Gábor István  associate professor, Department of Measurement and Information Systems, BME
    Dr. Pataki, Béla  associate professor, Department of Measurement and Information Systems, BME