Methods and Applications of Artificial Intelligence (ETF RIO MPVI 5970) |
|
General information |
|
Module title | Methods and Applications of Artificial Intelligence |
Module code | ETF RIO MPVI 5970 |
Study | ETF-B |
Department | Computing and Informatics |
Year | 2 |
Semester | 3 |
Module type | Mandatory |
ECTS | 7 |
Hours | 70 |
Lectures | 38 |
Exercises | 32 |
Tutorials | 0 |
Module goal - Knowledge and skill to be achieved by students |
|
| Objective of this course is to introduce students with advanced methods in artificial intelligence. Beginning with logic programming and optimization, reasoning methods based on uncertain or incomplete information, students will be able to easier comprehend methods of automatic learning, machine symbolic learning, machine learning based on neural networks and machine learning based on genetic programming. Based on the acquired knowledge, students will be ready to model and implement intelligent computer systems. | |
Syllabus |
|
| 1. Overview of artificial intelligence application areas <br> 2. Planning paradigms: linear, nonlinear and hierarchical planning, presentation of planning <br> 3. Logic programming and optimization: combinatorial optimization: an alternative to operations research, genetic algorithms, evaluation of GA, genetic optimization in combinatoric problems, application examples <br> 4. Knowledge based systems: overview of knowledge based systems (expert systems) technologies, classical reasoning methods, uncertain or incomplete information reasoning, statistical approaches, fuzzy logic based approach and fuzzy sets, adaptive fuzzy systems based on GA optimization, application examples <br> 5. Automatic learning: classical decision tree based learning methods, induction and deduction, weak methods in proofing theorem, proofing of resolution theorem <br> 6. Machine learning – symbol based: work environment for symbol based learning, search space exploration, knowledge and learning, unsupervised learning <br> 7. Machine learning – neural network based: introduction to artificial neural networks, supervised learning: perceptron, linear networks, nonlinear networks, radial networks, unsupervised learning: SOM and LVQ networks, recurrent networks, Elman networks, Hopfild networks <br> 8. Machine learning – genetic programming bases: genetic programming, classification systems and GP, artificial life, social based learning <br> |
|
Literature |
|
| Recommended | 1. Notes and slides from lectures (See Faculty WEB Site) <br> 2. Stuart J.Russel, Peter Norviq, Artificial Intelligence: A Modern Approach, Prentice Hall, 2002. <br> 3. George F. Luger and William A. Stubblefield, Artificial Intelligence, Structures and Strategies for complex Problem SolvingAddison Wesley, 1998. <br> 4. Neural Networks, Algorithms, Applications, an Programming Techniques, James A. Freeman, David M.Skapura, Addison-Wesley, 2001. <br> |
| Additional | 1. Neural Network Toolbox, The Mathworks, 2001 <br> 2. Genetic Algorithm Toolbox, The Mathworks, 2001 <br> 3.Z.Avdagić, Vještačka inteligencija& fuzzy-neuro-genetika Grafoart, 2003. <br> |
Didactic methods |
|
| Through lectures, students will learn about the theory, tasks and applicative examples within thematic units. Lectures consist of theoretical part, presentational descriptive examples, genesis and resolution of specific tasks. In this way, students will have basis for appliance of skilled material in engineering applications. Additional examples and exam tasks are discussed and solved during the laboratory exercises. Laboratory practice and home assignments will enable students of continuous work and their knowledge verification. | |
Exams |
|
| During the course students will collect points according to the following system: <br> - Attending lectures, exercises and tutorial classes: 10 points, student with more then three absences from lectures, exercises and/or tutorials can not achieve these points; <br> - Home assignments: maximum of 10 points, assuming solving 5 to 10 assignments evenly distributed throughout the semester; <br> - Partial exams: two written partial exams, maximum of 20 points for each positively evaluated partial exam; <br> Student who during the semester achieved less than 20 points must re-enroll this course. <br> Student who during the semester achieved 40 or more points will access to final oral exam, the exam consists of discussing the partial exams tasks, home assignments and answers to simple questions related to course topics. <br> Final oral exam provides maximum of 40 points. To achieve a positive final grade, students in this exam must achieve a minimum of 20 points. Students who do not achieve this minimum will access to makeup oral exam. <br> Student who during the semester achieved 20 or more points, and less than 40 points will access to makeup exam. Makeup exam is structured as follows: <br> - Written part structured in the same way as a partial written exam, during which students solve problems in topics they failed on partial exams (achieved less then 10 points), <br> - Oral part structured in the same way as a final oral exam. <br> Only students who, after passing the written part of the makeup exam managed to achieve a total score of 40 or more points, can access to oral makeup exam, where the score consists of points achieved through attending classes, home assignments, passing partial exams and passing the written part of makeup exam. <br> Oral makeup exam provides maximum of 40 points. To achieve a positive final grade, students in this exam must achieve a minimum of 20 points. Students who do not achieve this minimum must re-enroll this course. <br> |
|
Aditional notes |
|
| 1. Tools and software packages that will be used during the exercises: MATLAB, SIMULINK , Neural Network Toolbox, Fuzzy Toolbox and Genetic Algorithm Toolbox. | |