Skip to Content
Home /  Courses And Programs / Introduction to Deep Learning for Computer Vision

Deep Learning is a layered version of Machine Learning that began in the 1980s with Image Processing Engineering and the popular Computer Vision (CV) application.  Teaching computer programs to see and understand the content of images and videos is CV as the base model architecture of the course. However, Deep Learning has broadened its applications in the past decade and is now an extension of other Data Science frameworks.
This course is a comprehensive introduction to Deep Learning as an extension of Supervised Learning, Unsupervised Learning, Reinforcement Learning, Graph Data Science, Natural Language Processing, and Time Series Analysis.  The first two weeks are preparation for the implementations with a clear set of definitions, characteristics, and methodologies of today’s Deep Learning. Then, demonstrations begin with Multilayer Perceptron and Feedforward Artificial Neural Networks (ANN), and we learn the fundamental techniques of Hyperparameter Tuning using Tensorflow and Keras.  The Convolutional Neural Network (CNN) model architecture is the key and most widely deployed Deep Neural Network architecture for computer vision, as the first half of the course focuses on learning the building blocks and different model architectures.
The second half expands to the introduction of Deep Neural Network architectures such as Deep Neural Networks (DNN), Recurrent Neural Networks (RNN), Generative Adversarial Networks (GAN), and all the extensions of other Data Science frameworks.  The breadth of applications beyond CV is augmented reality, autonomous driving, unmanned Aerial Vehicles (UAV), forecasting human behavior, real estate image classification, stock market prediction, and many more.

Key Topics:

  • Deep Learning fundamentals and its application in real world
  • Application of deep learning in computer vision
  • Implementation of training of neural networks
  • Compression and pruning techniques

Learning Outcomes: 

  • Learn fundamentals of deep learning and the widespread network architectures employed in the real world for computer vision applications.
  • Implement and train your Neural Networks to understand how Deep Learning is used in Computer Vision and other applications.
  • Apply course content to develop, train, and fine-tune the Neural Network for your selected computer vision application and other applications.
  • 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 smartphones.

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)
Related Certificate Programs: Machine Learning Methods

+ Expand All