MEM1713

Course name:
Artificial Intelligence
Level: Postgraduate
Session:    
Semester 2, 2012/2013
Synopsis:
This course offers insights into the understanding of two artificial intelligence (AI) techniques namely, fuzzy logic and artificial neural networks (ANN). Both techniques have been successfully applied by many industries in consumer products and industrial systems. Fuzzy logic offers flexibility in developing rule-based systems using natural language type of rules. On the other hand, ANN have strong generalization and discriminant properties and offer a simple way of developing system models and function approximation. They are highly feasible in many pattern recognition applications. This course offers a basic understanding of the two AI techniques and their real world applications. This course might include hands-on experiments of fuzzy logic and ANN using a software developed by the Center for Artificial Intelligence & Robotics (CAIRO) and Augmented Innovation Sdn. Bhd., and other commercial software.
Objectives:
This course is intended to provide a basic understanding on the concepts of AI, which includes fuzzy logic and neural networks techniques, and some of their applications. The course has been organized to have the following objectives:
  1. To understand the broad concept of artificial intelligence and its applications in industry.
  2. To understand the basic principles of fuzzy logic and neural networks.
  3. To study several neural network algorithms.
  4. To study how fuzzy logic and neural networks are applied in some real world applications.
  5. To have some hands-on experience on using specialized teaching software for fuzzy logic and neural network applications.
Syllabus:
The following are the topics that are covered in this course:
  1. Introduction to Artificial Intelligence  
  2. Introduction to Fuzzy Logic
  3. Fuzzy Sets and Fuzzy Systems
  4. Fuzzy Logic Control Systems and Applications
  5. Introduction to Neural Networks 
  6. Simple Neural Networks
  7. Gradient Descent Learning Algorithm
  8. The Back-Error-Propagation Algorithm
  9. Radial Basis Function Neural Networks
  10. Neural Networks Applications and Case Studies
  11. Simulations of Fuzzy Logic Control Systems and Neural Networks
Time & Venue:
2.00 - 5.00 pm, P07-308
Assessment:
Test 1 (20%)
Test 2 (20%)
Assignment 1 (10%)
Assignment 2 (10%)
Final examination (40%)

Ċ
kumeresan danapalasingam,
Apr 28, 2013, 8:00 PM
Ċ
kumeresan danapalasingam,
Apr 25, 2013, 11:56 PM
Ċ
kumeresan danapalasingam,
Apr 25, 2013, 11:56 PM
Ċ
kumeresan danapalasingam,
May 12, 2013, 8:26 PM