Design, implement, and apply task-dependent deep learning architectures. Topics include mathematical overview of machine learning, deep feedforward networks, regularization for deep learning, optimization for training deep learning models, convolutional neural networks, recurrent neural networks, practical considerations and recent models and architectures in deep learning. Applications include signal processing and computer vision.

Background As a graduate course, students should have the following skills:

Calculus (BIT 1200), Linear Algebra (BIT 1201)
Probability & Statistics (BIT 2000, BIT 2009)
Ability to code in Python

ITEC 5900, Directed Studies

Directed Studies (DS) course allows students to work on a topic that is not offered as a regular course. Read the CSIT Graduate Manual for the procedure to follow before you can register. You must coordinate with a faculty member to submit a course outline and a Directed Study Registration Form.