Computer Vision (CV) is a study that teaches computers to see and understand the content of images and videos. CV has broad applications across many industries such as autonomous driving, medical imaging, public safety, home security, augmented reality, Unmanned Aerial Vehicles (UAV), and many others.
Deep learning is the driving force behind many recent advances in these CV applications. In this course, we will start by building a feedforward Artificial Neural Network (ANN) and learn the fundamental techniques of hyperparameter tuning using Tensorflow Keras. Convolutional Neural Network (CNN) is the key and most widely deployed deep neural network architecture for computer vision. Students will learn the building blocks of CNN and the history of the evolution of CNN architectures. Important concepts such as data augmentation and transfer learning to improve network performance and training will be covered.
- Learn fundamentals of deep learning and the popular network architectures employed in the real world for computer vision applications
- Implement and train your own neural networks to gain a deep understanding of how deep learning is used in computer vision
- Apply of course content to develop, train, and fine-tune the neural network for your selected computer vision application
- Learn new research and development area of deep learning running at the edge by understanding the techniques of compression and pruning and tool for deploying the deep learning model on the platform such as smartphone
Prerequisites: Basic proficiency in programming, college calculus, linear algebra, and probability and statistics
Next steps: You can continue learning by following Machine Learning Methods
Course Number: CSE-41388
Credit: 3.00 unit(s)
+ Expand All
1/10/2023 - 3/11/2023