Representation Learning
Please continue reading Deep Learning Book - Chapter 20: Deep Generative Models.
20.6 Convolutional Boltzmann Machines
20.7 Boltzmann Machines for Structured or Sequential Outputs
20.8 Other Boltzmann Machines
20.9 Back-Propagation through Random Operations
20.10 Directed Generative Nets
(This is the most important section. Many of the covered approaches are currently considered “hot topics” in deep learning.)
Your goal should be to understand the described approaches at a level that allows you to explain the fundamental ideas, differences (advantages and disadvantages) and specific challenges.
Deadline for questions to be considered in class is January 28, 7am. I will also try to accommodate things that come in later but I cannot make guarantees. The earlier you bring up questions, the better.
Like last week, we will spend about 50% of the time in class for discussing the reading assignments. This will leave less time for the course project. Therefore, if you would like to present and/or discuss progress on a specific aspect of the project, please prepare accordingly. Also, please send an email with the topic and the approximate amount of time required until January 30, 10am.