University of Colorado at Boulder
University of Colorado at Boulder Search A to Z Campus Map CU Search Links
ECE Home
Undergraduate
Graduate
Course List
Research
Contact Us

ECEN 4120 - Neural Network Design


Catalog Data ECEN 4120 (3). Neural Network Design. Introduces basic (artificial) neural network architectures and learning rules. Emphasis is placed on mathematical analysis of these networks, on methods of training them, and on their application to practical problems in areas such as pattern recognition, signal processing, and control systems. The course shows how to construct a network of "neurons" and train them to serve a useful function.
(Meets with ECEN 5120.)
Credits and Design 3 credit hours. Elective course.
Prerequisite(s) ECEN 1030, C Programming for EE/ECE, or CSCI 1300, Intro to Programming
APPM 2360, Linear Algebra and Differential Equations (or MATH 3130)
Textbook Hagan, Demuth, and Beale, Neural Network Design, PWS Publishing, 1996.
  
Course Objectives Neural networks are good at fitting non-linear functions and recognizing patterns. Consequently they have wide application in the aerospace, automotive, banking, defense, electronics, entertainment, financial, insurance, manufacturing, oil and gas, robotics, telecommunications and transportation industries.
Topics Covered
  1. Introduction
  2. Neuron model and network architecture
  3. Illustrative example
  4. Perceptron learning rule
  5. Signal and weight vector spaces
  6. Linear transformations for neural networks
  7. Supervised Hebb
  8. Performance surfaces and optimum points
  9. Performance optimization
  10. Widrow Hoff
  11. Backpropagation
  12. Variations on backpropagation

Last revised: 08-02-11, PM, ARP.