University of Colorado at Boulder
University of Colorado at Boulder Search A to Z Campus Map CU Search Links
ECE Home

ECEN Courses

Undergraduate
Graduate
Course List
Research
Contact Us

ECEN 5120 - Neural Network Design

Elective - 3 credit hours
Meets with ECEN 4120

On-Line Course Materials

Catalog Description: 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.

Prerequisites: CSCI 1300, Intro to Programming, and APPM 2360, Linear Algebra and Differential Equations

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:

  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
Class schedule: 3 hours of lecture per week.

Contribution of course to meeting Criterion 4, the professional component: This course provides 3 semester hours of electrical engineering topics consisting of engineering sciences and engineering design.

Relationship of course to program outcomes: This course is not required and is not included in outcomes assessment.

Prepared by: Howard Demuth, Vincent Heuring
May 16, 2005.