Deep Learning in Computer Vision

Student Learning Outcomes, Goals, Objectives:

The goal of this course is to help students understand the fundamentals of machine learning

and deep learning theories and techniques, which are highly related to computer vision topics, and

experience practical solutions to modern computer vision challenges through assignments/projects.

Particularly, the topics covered in this course include several state-of-the-art deep learning architectures,

e.g., convolutional neural networks, recurrent neural networks and generative adversarial networks, and

their extended and improved versions.

Students successfully completing this course will be able to:

• Understand the concept of deep neural networks and utilize deep learning platforms.

• Interpret factors related to deep learning model’s performance and generalizability.

• Implement discriminative and generative deep learning architectures.

• Demonstrate knowledge of advanced deep learning architectures for different computer vision tasks.

• Create an end-to-end work product for task-specific deep learning.

• Analyze and demonstrate the project results.

Course Grading Information:

Activity/Performance Measure	Percentage/Points
Assignments	20%
Project	20%
Tests	60%

Grading Scale

Percentage	Letter Grade
94-100	A
90-93	A-
87-89	B+
84-86	B
80-83	B-
77-79	C+
74-76	C
70-73	C-
67-69	D+
64-66	D
60-63	D-
<59	F

Attendance/Participation:

Attendance/participation is not a graded component included in the student's final grade for this course.

Course Materials Purchased by the Students:

No course materials are required.