1. GENERAL SPECIFICATIONS
Course : Artificial Intelligence
Code of Course : 207008
Course duration : 17 weeks
Teaching Methodology : Technical - experimental
Hours per week : Theory: 3h – Laboratory: 2h
Nature: Professional Training
Number of credits : Four (04)
Prerequisites : 205007 – Operations Research I
Academic Semester : 2012 – I
Coordinator:
Code of Course : 207008
Course duration : 17 weeks
Teaching Methodology : Technical - experimental
Hours per week : Theory: 3h – Laboratory: 2h
Nature: Professional Training
Number of credits : Four (04)
Prerequisites : 205007 – Operations Research I
Academic Semester : 2012 – I
Coordinator:
2. ABSTRACT
Artificial Intelligence, concepts, paradigms and application in industry and services. Knowledge representation. AI problem representation as search in state space. Blind and informed search methods. Man-machine intelligent games. Expert Systems, architecture, taxonomy and applications. Inference engine. Knowledge Engineering, concepts, evolution, CommonKADS Methodology. Quality and Validation of Expert Systems, Introduction to Machine Learning (Automatic Learning) and heuristic.
3. GENERAL OBJECTIVE
Students will gain knowledge in the area of Artificial Intelligence in general and they will develop basic aspects in the development of intelligent games and expert systems, and its applicationn in the resolution of problems in the areas of industry and services.
4. SPECIFIC OBJECTIVES
After finishing the course, students will be able to:
1. Understand that is Artificial Intelligence and complexity of their problems.
2. Represent and solve human game - machine through search techniques in a state space.
3. Knowing the different search strategies blind and informed.
4. Design and develop game software intelligent man-machine interaction and usingartificial intelligence techniques.
5. Understand what they are expert systems and know when to use them.
6. Knowing which is the Knowledge Engineering and a method for developingknowledge-based systems
7. Evaluate the quality of expert systems solution.
8. Design and develop expert systems based on different inference engines (methodschaining), considering quality criteria.
9. Understand the concepts of machine learning and heuristic, its importance and its applications in industry and services.
1. Understand that is Artificial Intelligence and complexity of their problems.
2. Represent and solve human game - machine through search techniques in a state space.
3. Knowing the different search strategies blind and informed.
4. Design and develop game software intelligent man-machine interaction and usingartificial intelligence techniques.
5. Understand what they are expert systems and know when to use them.
6. Knowing which is the Knowledge Engineering and a method for developingknowledge-based systems
7. Evaluate the quality of expert systems solution.
8. Design and develop expert systems based on different inference engines (methodschaining), considering quality criteria.
9. Understand the concepts of machine learning and heuristic, its importance and its applications in industry and services.
5. ANALYTICAL CONTENT PER WEEKS
Week | Theme | Theory Works | Laboratory Works |
---|---|---|---|
1
|
|
||
2
|
|
||
3
|
|
||
4
|
|
||
5
|
|
||
6
|
|
||
7
|
|
||
8
|
Partial Exam | ||
9
|
Presentation of computational work
|
||
10
|
|
||
11
|
Development of rule-based expert systems
|
||
12
|
|
||
13
|
Introduction to Machine Learning.
|
||
14
|
|
||
15
|
Presentation of computational work
|
||
16
|
Final Exam. | ||
17
|
Substitute Exam (Only for those who did not give partial or final exam). |
6. METHODOLOGY
The course is developed through theoretical activities - practices, emphasizingapplications in industry and services. The students were divided into teams of 3 going to develop two computational works. During the theory sessions will discuss the proposed problem solving. During the laboratory sesciones readings as well as evaluate the progress of the work computer.
7. EVALUATION
The final average (PF) is determined as follows:PF = 0.025 (CL1 + CL2 + CL3 + CL4) + 0.075 (TB1 + TB2) + 0.15 * 0.30 * LA + (EA +EB)
Where:
CLx: Reading Controls (CL1, CL2, CL3 and CL4)
TB1: Group Work (Games Smart Man - Machine)
TB2: Group Work (Expert Systems)
EA: Partial Review
EB: Final Exam
LA: Laboratory
The student may replace the exam partial or final if unable to provide any of these tests.Students will be evaluated only showing 70% or more assists.
8. BIBLIOGRAPHY
STUART, RUSSELL, PETER, Norvig2010 Artificial Intelligence: A Modern Approach (3rd Edition). Prentice Hall Ed.
ISBN-13: 978-0136042594
PATRICK, WINSTON
Artificial Intelligence 1984. Ed Addison-Wesley
ISBN 0-201-51876-7
ELAINE RICH
Artificial Intelligence 1988. Ed McGraw-Hill
ISBN 0-07-450364-2
DAVID, Mauritius
Notes in Artificial Intelligence 2000.
BONIFACE, MARTIN, ALFREDO, SANZ
2002 Neural Networks and Fuzzy Systems. Ed Alfaomega
ISBN 84-7897-466-0
Giarratano RILEY
2001 Expert systems, principles and programming. Ed Thomson Science
ISBN 970-686-059-2
The required readings will be provided by the course instructor