Please visit the Coronavirus information site for the latest updates regarding UM-Dearborn's COVID-19 response.

About the Program

This certificate program introduces students to the core concepts of intelligent systems and a broad range of techniques for building, testing and evaluating intelligent systems. Topics include: intelligent system design, training and evaluation, decision trees, rule based systems, Bayesian learning, Support Vector Machines, neural network systems, and fuzzy systems. A variety of application cases will be studied in the courses under this program. (12 credits hours)

Certificate offered on Campus and via Distance Learning 

Required Core Courses

ECE 579: Intelligent Systems

Topics to be covered include: intelligent systems design, training and evaluation, decision trees, Bayesian learning, and reinforcement learning. A project will be required. (3 credits)

Course Descriptions

Complete 3 courses from the following (9 credits):

ECE 537: Data Mining

Advances in computer information systems, machine learning, statistics, and intelligent systems and methodologies for the automatic discovery of knowledge from large high-dimensional databases will be discussed. This course also uses engineering development tools such as neural networks, fuzzy logic, and genetic algorithms. (3 credits)

ECE 552: Fuzzy Systems

A study of the concept of fuzzy set theory is discussed including operations on fuzzy sets, fuzzy relations, fuzzy measures, fuzzy logic, with an emphasis on engineering application. Topics to be covered include fuzzy set theory, applications to image processing, pattern recognition, artificial intelligence, computer hardware design, and control systems. (3 credits)

ECE 5831: Pattern Recognition and Neural Networks

Students will gain an understanding of the language, formalism, and methods of pattern recognition. Various solution approaches will be covered including statistical methods and neural network-based methods. Students will learn how to mathematically pose various pattern recognition problems and analytically derive some well-known statistical results and learning rules. In addition, the student will learn how to perform computer simulations of various statistical and neural network models and learn how to select appropriate model parameters, such as network architecture, hidden layer size, and learning rate. Case Studies will be presented to illustrate a variety of applications. (3 credits)

ECE 576: Information Engineering

This course will cover the fundamental concepts of information engineering including computation, storage, communication, and application. Examples of topics are multimedia data such as video, audio, image and text, multimedia transmission through local and wide area networks, multimedia data representations, storage and compression. Information engineering applications will be discussed and students are expected to complete a project in a selected application. (3 credits)

Learning Goals and Outcomes

  1. Students will have knowledge in the core concepts of intelligent systems and a broad range of techniques for building, testing and evaluating intelligent systems. 
  2. Students will have knowledge in topics such as: intelligent system design, training and evaluation, decision trees, rule based systems, Bayesian learning, Support Vector Machines, neural network systems, and fuzzy systems.  

Admission Requirements

Applicants must possess an undergraduate degree in Electrical Engineering with an overall GPA of 3.0 or higher.

Tentative Course Schedules

ECE 579

Winter

ECE 537

Fall

ECE 552

Summer

ECE 5831

Fall

ECE 5831

Fall

ECE 576

Fall

CECS Graduate Education Office

1184/1186
Heinz Prechter Engineering Complex (HPEC)
Phone: 
313-593-0897
Fax: 
313-593-9967
Back to top of page