This module introduces computer vision and deep learning, covering a variety of
essential topics to provide students with the knowledge and practical skills needed
to succeed in this exciting field. Students will learn about the history of computer
vision and image formation, as well as practical skills like edge detection, image
features, SIFT, image matching, and image segmentation. The course also introduces
linear programming, tensors, and GPUs, before delving into the essential concepts of
perceptrons and neural networks. Students will learn how to optimize neural networks
as well as investigate a variety of deep learning topics such as convolutional
neural networks, activation functions, loss, learning rates, and CNN architectures.
The module also introduces PyTorch and covers the essential steps for preparing
datasets, building, training, testing, and validating models. The highlight of the
module is a practical image classification project using PyTorch, which lays a
strong foundation in both theory and practical applications.
Computer Vision and Deep Learning are changing the way everything works
today, from airplanes to autonomous cars. This module introduces students to
the fundamentals of these state-of-the-art technologies.
This module prepares the students to start working on applications in
various fields, such as healthcare, transportation, and entertainment.
This module prepares students for basic internships in both small and large