Deep learning often works great on pattern recognition tasks where the test data resembles the training data.  But what to do when the task is more complicated?  This course will explore recently developed approaches for learning algorithms.

Topics will include: Algorithm unfolding, recurrent neural networks (RNNs), neural programming, neural Turing machines, neural GPUs

This is a “reading course,” meaning that students will read and present papers from the technical literature to the rest of the class in a lively debate format.  Discussions will aim at identifying common themes and important trends in the field.  Students will also obtain valuable hands on experience through a group project.

• Location: Zoomland
• Time: Friday 245pm
• Instructors: Richard Baraniuk and Hamid Javadi
  Office Hours: By appointment
• Prerequisites: Required: Linear algebra, introduction to probability and statistics, familiarity with a programming language such as Python, R, or MATLAB.  Desired: Knowledge of machine learning, deep learning, signal processing, and optimization
• Course Website:  Piazza Course Management Site (It is mandatory that you use this site; all official announcements will be made there)