Fundamentals of Artificial Intelligence
IZU Acad. year 2010/2011 Summer semester 4 credits
Problem solving, state space search, problem decomposition, games playing. Knowledge representation. AI languages (PROLOG, LISP). Machine learning principles. Statistical and structural pattern recognition. Fundamentals of computer vision. Base principles of natural language processing. Application fields of artificial intelligence.
Language of instruction
Subject specific learning outcomes and competences
Students acquire knowledge of various approaches of problem solving and base information about machine learning, computer vision and natural language processing. They will be able to create programs using heuristics for problem solving.
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 computer vision and natural language processing.
Prerequisite kwnowledge and skills
- Russel,S., Norvig,P.: Artificial Intelligence, Prentice-Hall, Inc., 1995, ISBN 0-13-360124-2, second edition, 2003, ISBN 0-13-080302-2
- Russel,S., Norvig,P.: Artificial Intelligence, Prentice-Hall, Inc., 1995, ISBN 0-13-360124-2, second edition 2003, ISBN 0-13-080302-2
- 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
Syllabus of lectures
- Introduction, types of AI problems, solving problem methods (BFS, DFS, DLS, IDS).
- Solving problem methods, cont. (BS, UCS, Backtracking, Forward checking, Min-conflict).
- Solving problem methods, cont. (BestFS, GS, A*, IDA, SMA, Hill Climbing, Simulated annealing).
- Solving problem methods, cont. (Problem decomposition, AND/OR graphs).
- Methods of game playing (minimax, alpha-beta, games with unpredictability).
- Logic and AI, resolution and it's application in problem solving.
- Knowledge representation (representational schemes).
- Implementation of basic search algorithms in PROLOG.
- Implementation of basic search algorithms in LISP.
- Machine learning.
- Fundamentals of pattern recognition theory.
- Principles of computer vision.
- Principles of natural language processing.
Syllabus of computer exercises
- Problem solving - simple programs.
- Problem solving - games playing.
- PROLOG language - basic information.
- PROLOG language - simple individual programs.
- LISP language - basic information.
- LISP language - simple individual programs.
- Simple programs for pattern recognition.
- Mid-term written examination - 20 points
- Programs in computer exercises - 20 points
Written mid-term exam
At least 15 points earned during semester.
Course inclusion in study plans