EE 484 - Neural Networks

3 lecture hours 0 lab hours 3 credits

Course Description
This course introduces students to the basic concepts of modeling systems using neural networks. The underlying concepts of neural networks are introduced, as well as a number of common topologies and learning rules used in neural networks, including deep learning. Students gain firsthand experience in the creation, training, and application of neural networks through computer assignments and a short research project. (prereq: (EE 2510 or CS 1011 or BE 2200) and MA 383)

Course Learning Outcomes
Upon successful completion of this course, the student will be able to:

Describe the basic configurations of neural networks
Describe and implement neural networks
Formulate engineering problems for which neural networks may be a suitable solution
Evaluate the suitability of neural network architectures and learning algorithms for engineering problems
Use commercially available neural network development tools
Interpret and critique scholarly articles in the area of neural networks

Prerequisites by Topic

High-level language programming with objects or structures
Calculus (gradients, series expansions)
Matrix arithmetic

Course Topics

Introduction to neural networks, problems, terminology, MATLAB toolbox (2 classes)
Data gathering and formatting (2 classes)
Linear perceptron and multilayer backpropagation networks (4 classes)
Training algorithms and associated mathematics (4 classes)
Radial basis networks (3 classes)
Self-organizing maps (1 class)
Time series networks, control systems, and adaptive filtering (4 classes)
Deep learning (3 classes)
Special topics (2 classes)
Project workshops (5 classes)

Coordinator
Dr. Sheila Ross

Print this Page

Announcement

The Raider Return

Milwaukee School of Engineering

Connect With MSOE

EE 484 - Neural Networks