Title:

Fundamentals of Artificial Intelligence

Code:IZU
Ac.Year:2017/2018
Term:Summer
Curriculums:
ProgrammeBranchYearDuty
IT-BC-3BIT2ndCompulsory
Language:Czech
Private info:http://www.fit.vutbr.cz/study/courses/IZU/private/
Credits:4
Completion:accreditation+exam (written)
Type of
instruction:
Hour/semLecturesSem. ExercisesLab. exercisesComp. exercisesOther
Hours:2600130
 ExaminationTestsExercisesLaboratoriesOther
Points:60202000
Guarantee:Zbořil František V., doc. Ing., CSc., DITS
Lecturer:Zbořil František, doc. Ing., Ph.D., DITS
Zbořil František V., doc. Ing., CSc., DITS
Instructor:Goldmann Tomáš, Ing., DITS
Kanich Ondřej, Ing., DITS
Rozman Jaroslav, Ing., Ph.D., DITS
Samek Jan, Ing., Ph.D., DITS
Semerád Lukáš, Ing., DITS
Šoková Veronika, Ing., DITS
Uhlíř Václav, Ing. et Ing., DITS
Žák Marek, Ing., DITS
Faculty:Faculty of Information Technology BUT
Department:Department of Intelligent Systems FIT BUT
Substitute for:
Artificial Intelligence (UIN), DITS
Schedule:
DayLessonWeekRoomStartEndLect.Gr.St.G.EndG.
MonlecturelecturesE11211:0012:502BIB
MonlecturelecturesE10411:0012:502BIB
MonlecturelecturesE10511:0012:502BIB
MonlecturelecturesE11211:0012:503BITxxxx
TuelecturelecturesE11213:0014:502BIA
TuelecturelecturesE10413:0014:502BIA
TuelecturelecturesE10513:0014:502BIA
TuelecturelecturesE11213:0014:503BITxxxx
 
Learning objectives:
  To give the students the knowledge of fundamentals of artificial intelligence, namely knowledge of problem solving approaches, machine learning principles and general theory of recognition. Students acquire base information about expert systems, computer vision and natural language processing.
Description:
  Problem solving: State space search (BFS, DFS, DLS, IDS, BS, UCS, Backtracking, Forward checking, Min-conflict, BestFS, GS, A*, Hill Climbing, Simulated annealing methods). Solving of optimization problems using algorithms inspired by nature (GA, ACO and PSO). Problem decomposition (And Or graphs), games playing (Mini-Max and Alfa-Beta algorithms). AI languages (PROLOG, LISP) and implementations of basic search algorithms in these languages. Machine learning principles. Statistical and structural pattern recognition. Basic principles of expert systems. Fundamentals of computer vision. Base principles of natural language processing. Application fields of artificial intelligence.
Knowledge and skills required for the course:
  
  • Basic knowledge of the programming in any procedural programming language.
  • Knowledge of secondary school level matematics.
Subject specific learning outcomes and competences:
  
  • Students will learn terminology in Artificial Intelligence field both in Czech and in English language.
  • Students will learn read and so partly write logic and functional programs.
Generic learning outcomes and competences:
  
  • Students will acquaint with problem solving methods based on state space search and on decomposition problem into sub-problems.
  • Students will acquaint with basic game playing methods of two players.
  • Students will learn to solve optimization problems.
  • Students will acquaint with fundamentals of propositional and predicate logics and with their applications.
  • Students will learn how to use basic methods of machine learning.
  • Students will acquaint with fundamentals of machine vision and natural language processing.
Syllabus of lectures:
 
  1. Introduction, Artificial Intelligence (AI) definition, types of AI problems, solving problem methods.
  2. State space search methods.
  3. Solving methods using decomposition problems into sub-problems (AND/OR graphs).
  4. Solving of optimization problems using algorithms inspired by nature - short introduction into Genetic algorithms, ACO (Ant Colony Optimization) and PSO (Particle Swarm Optimization).
  5. Methods of game playing (minimax, alpha-beta, games with unpredictability).
  6. Logic and AI, resolution and it's application in problem solving.
  7. Implementation of basic search algorithms in PROLOG.
  8. Implementation of basic search algorithms in LISP.
  9. Machine learning.  
  10. Fundamentals of pattern recognition theory. Classical classifiers, perceptron.
  11. Expert systems.
  12. Principles of computer vision.
  13. Principles of natural language processing.
Syllabus of computer exercises:
 
  1. Problem solving - simple programs.
  2. Problem solving - games playing.
  3. PROLOG language - basic information.
  4. PROLOG language - simple individual programs.
  5. LISP language - basic information.
  6. LISP language - simple individual programs.
  7. Simple programs for pattern recognition.
Fundamental literature:
 
  • Russel,S., Norvig,P.: Artificial Intelligence, Prentice-Hall, Inc., 1995, ISBN 0-13-360124-2, second edition 2003, ISBN 0-13-080302-2, third edition 2010, ISBN 0-13-604259-7
  • Luger,G.F.: Artificial Intelligence - Structures and strategies for Complex Problem Solving, 6th Edition,
    Pearson Education, Inc., 2009, ISBN-13: 978-0-321-54589-3, ISBN-10: 0-321-54589-3
Study literature:
 
  • Russel,S., Norvig,P.: Artificial Intelligence, Prentice-Hall, Inc., 1995, ISBN 0-13-360124-2, second edition 2003, ISBN 0-13-080302-2, third edition 2010, ISBN 0-13-604259-7
Progress assessment:
  
  • Mid-term written examination - 20 points.
  • Programs in computer exercises - 20 points.
  • Final written examination - 60 points; The minimal number of points which can be obtained from the final written examination is 25. Otherwise, no points will be assigned to a student.
Exam prerequisites:
  At least 15 points earned during semester (mid-term test + programs in computer exercises).