University of Technology, Sydney

Staff directory | Webmail | Maps | Newsroom | What's on

49275 Neural Networks and Fuzzy Logic

6cp; 3hpw, on campus; availability: all courses
Requisite(s): 120 credit points of completed study in spk(s): C10061 Bachelor of Engineering Diploma Engineering Practice OR 120 credit points of completed study in spk(s): C10066 Bachelor of Engineering Science OR 120 credit points of completed study in spk(s): C10067 Bachelor of Engineering OR 120 credit points of completed study in spk(s): C09067 Bachelor of Engineering (Honours) Diploma Professional Engineering Practice OR 120 credit points of completed study in spk(s): C09066 Bachelor of Engineering (Honours) OR 120 credit points of completed study in spk(s): C10065 Bachelor of Engineering Bachelor of Business OR 120 credit points of completed study in spk(s): C10068 Bachelor of Engineering Bachelor of Business Diploma Engineering Practice OR 120 credit points of completed study in spk(s): C09070 Bachelor of Engineering (Honours) Bachelor of Business OR 120 credit points of completed study in spk(s): C09071 Bachelor of Engineering (Honours) Bachelor of Business Diploma Professional Engineering Practice OR 120 credit points of completed study in spk(s): C10339 Bachelor of Engineering Bachelor of Creative Intelligence and Innovation OR 120 credit points of completed study in spk(s): C09076 Bachelor of Engineering (Honours) Bachelor of Creative Intelligence and Innovation
These requisites may not apply to students in certain courses.
There are course requisites for this subject. See access conditions.
Recommended studies:

Introductory programming or introductory control subjects


UTS: Engineering: Electrical, Mechanical and Mechatronic Systems


Postgraduate

Description

The principal objective of this subject is to introduce students to neural networks and fuzzy theory from an engineering perspective. This is a hands-on subject where students are given integrated exposure to professional practice. In the identification and control of dynamic systems, neural networks and fuzzy systems can be implemented as model-free estimators and/or controllers. As trainable dynamic systems, these intelligent control systems can learn from experience with numerical and linguistic sample data.

Typical availability

Autumn session, City campus


Detailed subject description.

Fee information

Information to assist with determining the applicable fee type can be found at Understanding fees.

Access conditions

Note: The requisite information presented in this subject description covers only academic requisites. Full details of all enforced rules, covering both academic and admission requisites, are available at access conditions and My Student Admin.