CS 5821 - Neural Networks & Deep Learning

Credits: 4

The majority of data in the world is unlabeled and unstructured, for instance images, sound, and text data. Shallow neural networks cannot easily capture relevant structures within this type of data, but deep networks are capable of discovering the hidden structures. Therefore, the
demand for deep learning skills is continuing to grow, as AI becomes more pervasive in our societies. In this course, you will learn about some of the inspiring and motivating applications of deep learning. You will learn about artificial neural networks and how they learn and optimize their parameters for a given task or application, and you will learn about deep learning models such as convolutional neural networks, recurrent neural networks and autoencoders.

Ultimately, the student will apply their knowleegde using tools such as the Keras and TensorFlow library to build different deep learning models and apply deep learning on different types of data to solve real world problems.

Prerequisites
C or better in CS 4410 or CS 5810.