ELEC 475 Computer Vision with Deep Learning Units: 3.50
Deep learning methods are highly effective at solving many problems in computer vision. This course serves as an introduction to these two areas and covers both the theoretical and practical aspects required to build effective deep learning-based computer vision applications. Topics include classification, convolutional neural networks, object detection, encoder-decoders, segmentation, keypoint and pose estimation, generative adversarial networks, and transformers. Labs and assignments will emphasize practical implementations of deep learning systems applied to computer vision problems.
(Lec: 3, Lab: 0.5, Tut: 0)
(Lec: 3, Lab: 0.5, Tut: 0)
Offering Term: F
CEAB Units:
Mathematics 0
Natural Sciences 0
Complementary Studies 0
Engineering Science 31
Engineering Design 11
Offering Faculty: Smith Engineering
Course Learning Outcomes:
- Describe the objectives of Computer Vision, and how these are addressed using Machine Learning methods.
- Describe the fundamental Machine Learning structures, including Multi-Layer Perceptrons, Convolutional Neural Networks, and Transformers.
- Identify the main problem areas of Machine Learning-based Computer Vision, including Autoencoders, Image Classification, Object Detection, Segmentation, Variational Autoencoders, Generative Adversarial Networks, and Visual Information Transformers.
- Explain the major architectural innovations that have advanced the performance of Machine Learning-based Computer Vision.
- Implement, train and test Machine Learning-based Computer Vision solutions.