Course Notes
The notes written by students and edited by instructors
-
Lecture 18: Deep Generative Models (Part 2)
GANs and their variations, Normalizing Flows and Integrating domain knowledge in DL.
-
Lecture 17: Deep generative models (part 1)
Overview of the theoretical basis and connections of deep generative models.
-
Lecture 16: Building Blocks of Deep Learning
Overview of CNNs, RNNs, and attention.
-
Lecture 15: Statistical and Algorithmic Foundations of Deep Learning
How graphical models relate to deep learning.
-
Lecture 14: Approximate Inference: Markov Chain Monte Carlo
An introduction of Markov Chain Monte Carlo methods.
-
Lecture 13: Approximate Inference: Monte Carlo and Sequential Monte Carlo Methods
Wrapping up variational inference, and overview of Monte Carlo methods.
-
Lecture 12: Theory of Variational Inference: Marginal Polytope, Inner and Outer Approximation
Introduction of Loopy Belief Propagation algorithm and the theory behind it and Mean-field approximation.
-
Lecture 11: Kalman Filtering and Topic Models
Kalman Filtering and Topic Models. See abstract. Due to the previous lecture running over, the actual material covered in the lecture deviated from what the lecture schedule suggests.
-
Lecture 10: Sequential Models
Introducing State Space Models and Kalman filters.
-
Lecture 9: Modeling Networks
Classic network learning algorithms.