ECE 597B: INTELLIGENT SYSTEMS

Organization:	Lectures
Prerequisites:	Differential Equations, Linear Algebra, Basic Probability
Requirements:	1. Homework Assignments (5-7), 30% 2. Midterm Exam, 35% 3. Term Project, 35%
Goals:	This course will cover a wide range of tools and methods in the design, analysis, optimiza- tion and control of industrial systems to pre- pare students for the modern industrial enviro- ment. The topics will include neural networks and its application in complex system modeling, fuzzy logic, information fusion methods, optimi- zation schemes and their applications. MATLAB will be the software platform.
Office Hours:
TA:
Books:
Lecture Notes:	chapter 1,chapter 2, chapter 3,chapter 4, chapter 5
Lab Project:	Handwritten Letter Recognition Term Project Example

COURSE OUTLINE

1. OPTIMIZATION METHODS

   1.1. Gradient methods
   1.2. Linear Programming
   1.3. Constrained Problems and Lagrange Multiplier Method
   1.4. Search Method
   1.5. Ordinal Optimization
   1.6. Genetic Algorithms
   1.7. Application
   

2. FUNDAMENTALS OF NEURAL NETWORKS

   2.1. Basic concepts
   2.2. Backpropagation algorithm
   2.3. Applications
   

3. ADVANCED NEURAL NETWORKS

   3.1. Competitive learning
   3.2. Data clustering networks
   3.3. Application in hierarchical modeling for complex systems
   3.4. Other application examples.
   

4. KNOWLEDGE REPRESENTATION METHODS

   4.1. Linguistic knowledge respresentation
   4.2. Mathematical foundation: Random Sets
   4.3. Applications
   

5. INFORMATION FUSION TECHNIQUES

   5.1. Fusion of linguistic and stochastic information
   5.2. Application in intelligent segementation
   5.3. Application in sensor fusion
   

Comments, Questions and Suggestions to Yang guo
Web Page Manager, at yguo@ecs.umass.edu