Subject: Computer Science
Credit units: 3
Offered: Either Term 1 or Term 2
Weekly hours: 3 Seminar/Discussion hours
College: Graduate and Postdoc Studies
Department: Computer Science


A survey of Deep Learning research topics in computer vision and data science. Deep learning techniques may include Deep Neural Networks, Convolutional Neural Networks, Recurrent Networks, Deep Generative Models and Reinforcement Learning. Application domains will focus on computer vision problems, including image classification, object detection and image segmentation. Additional application domains relevant to graduate students taking the course will be included. Software tools will be introduced for practical application.

Note: Instructor approval required. Students may not receive credit for both CMPT 489 and CMPT 828.

Upcoming class offerings

For full details about upcoming courses, refer to the class search tool or, if you are a current student, the registration channel in PAWS.


The syllabus is a public document that provides detail about a class, such as the schedule of activities, learning outcomes, and weighting of assignments and examinations.

Once an instructor has made their syllabus publicly available on USask’s Learning Management System, it will appear below. Please note that the examples provided below do not represent a complete set of current or previous syllabus material. Rather, they are presented solely for the purpose of indicating what may be required for a given class. Unless otherwise specifically stated on the content, the copyright for all materials in each course belongs to the instructor whose name is associated with that course. The syllabus is the intellectual property of instructors or the university.

For more information, visit the Academic Courses Policy , the Syllabus page for instructors , or for students your Academic Advising office.