University of Wisconsin - Madison 
Department of Electrical and Computer Engineering

ECE/CS/ME 539 Introduction to Artificial Neural Network and Fuzzy Systems

COURSE DESCRIPTION

Fall 2008

• Time and Place: (Lec 1) MWF 2:25 - 3:15 PM Class room: 2540 Engr. Hall
  
• Instructors: Yu Hen Hu , 3625 Engr. Hall, Tel.262-6724, E-mail: hu@engr.wisc.edu.
  Office hours:
• Credits:  3
• Prerequisite: Math 340, or ECE 330, or consent of instructor. CS 302, or CS 310. Knowledges of Matlab, matrix/vector notations, numerical linear algebra operations (e.g. eigenvalue/ singular value decomposition) , probability theory and statistics (e.g. hypothesis testing, estimation, statistical decision theory) are essential.
• Goals: This course presents an overview of the theory and applications of artificial neural network and fuzzy systems to engineering applications with emphasis on signal processing and control. The objective of this course is on the understanding of various neural network and fuzzy systems models and the applications of these models to solve engineering problems.
• Topics:
  • Learning paradigms, perceptron learning
  • Multi-Layer Perceptron and Back-propagation learning
  • Pattern classification
  • Support vector machines
  • Clustering, Self-Organization Map, Radial Basis Network,
  • Time series analysis, system identification and expert system applications
  • Fuzzy Set Theory and Fuzzy Logic Control
  • Genetic Algorithm and Evolution Computing
  • Recurrent Network, Hopfield network (time permit)
• Textbook:
  1. Neural Networks: A Comprehensive Foundation, Simon Haykin, Prentice Hall, New Jersey, second edition, 1999. (required)
  2. Handbook of Neural Network Signal Processing, Y. H. Hu and J.-N. Hwang, CRC Press, 2002 ( Optional )
  3. Advanced Fuzzy Systems Design and Applications, Yaochu Jin, Physica-Verlag Heidelberg, 2003, ISBN 3-7908-1537-3. (Optional)
  4. A set of class notes will be available on the web. Instructor will give password to access the notes.
• Computer Usage: Individual projects will be assigned during the semester require to program or use nerual network/fuzzy system simulators using C/C++/Java or other high level programming language, or Matlab, or existing public domain packages
• Grading Policy (tentative):
  • 30% three to four assignments
  • 15% Midterm (evening exam)
  • 25% Take home final exam
  • 30% Indivisual Term Project

  Go to Course Outline or back to ECE 539 Home Page.