| 1 | Tue
Sept 22 | - Introduction [slides]
- Probability Background and Basic Results [slides]
| |
Wed
Sept 23 | - Probability Background and Basic Results
- Basic Assumptions for Efficient Model Representation [slides]
|
Thu
Sept 24 | - Directed Graphical Models
[slides I] [slides II] [notes] [self-study exercises] [self-study solutions]
|
| 2 | Tue
Sept 29 | - Directed Graphical Models
| |
Wed
Sept 30 | - Directed Graphical Models
- Undirected Graphical Models
[slides I] [slides II] [notes] [self-study exercises] [self-study solutions]
|
Thu
Oct 1 | - Undirected Graphical Models
|
| 3 | Tue
Oct 6 | - Undirected Graphical Models
- Expressive Power of Graphical Models
[slides] [notes] [self-study exercises] [self-study solutions]
| Tutorial 1 |
Wed
Oct 7 | - Expressive Power of Graphical Models
- Exact inference
[slides] [notes] [self-study exercises] [self-study solutions]
|
Thu
Oct 8 | |
| 4 | Tue
Oct 13 | | Tutorial 2 |
Wed
Oct 14 | - Exact inference
- Exact inference for Hidden Markov Models
[slides] [notes] [self-study exercises] [self-study solutions]
|
Thu
Oct 15 | - Exact inference for Hidden Markov Models
- Optional: Python notebook on HMMs (check out the basics and inference notebooks for a simple language model and how to run inference on it)
|
| 5 | Tue
Oct 20 | - Actions and their Effects (Causality)
[slides] [notes] [self-study exercises] [self-study solutions]
| Tutorial 3 |
Wed
Oct 21 | - Actions and their Effects (Causality)
- Decision making under uncertainty
[slides] [notes] [self-study exercises] [self-study solutions]
|
Thu
Oct 22 | - Decision making under uncertainty
|
| 6 | Tue
Oct 27 | - Decision making under uncertainty
- Basics of Model-Based Learning
[slides] [notes] [self-study exercises] [self-study solutions]
| Tutorial 4 |
Wed
Oct 28 | - Basics of Model-Based Learning
|
Thu
Oct 29 | - Basics of Model-Based Learning
- Factor Analysis and Independent Component Analysis
[slides] [notes] [self-study exercises] [self-study solutions]
|
| 7 | Tue Nov 3 | - Factor Analysis and Independent Component Analysis
- Intractable Likelihood Functions [slides]
| Tutorial 5 |
Wed
Nov 4 | - Intractable Likelihood Functions
- Variational Inference and Learning I: Fundamentals, mean-field VI, and the EM algorithm
[slides] [notes] [self-study exercises] [self-study solutions]
|
Thu
Nov 5 | - Variational Inference and Learning I: Fundamentals, mean-field VI, and the EM algorithm
|
| 8 | Tue
Nov 10 | - Variational Inference and Learning I: Fundamentals, mean-field VI, and the EM algorithm
- Learning for Hidden Markov Models
[slides] [notes] [self-study exercises] [self-study solutions] - Optional: Python notebook on HMMs (check out the learning notebooks)
| Tutorial 6 |
Wed
Nov 11 | - Learning for Hidden Markov Models
|
Thu
Nov 12 | - Learning for Hidden Markov Models
- Variational Inference and Learning II: Modern VI and Variational Autoencoders
[slides] [notes] [self-study exercises] [self-study solutions] - Optional: Python notebook on VAEs
|
| 9 | Tue
Nov 17 | - Variational Inference and Learning II: Modern VI and Variational Autoencoders
| Tutorial 7 |
Wed
Nov 18 | - Variational Inference and Learning II: Modern VI and Variational Autoencoders
- Sampling and Monte Carlo Integration
[slides] [notes] [self-study exercises] [self-study solutions]
|
Thu
Nov 19 | - Sampling and Monte Carlo Integration
|
| 10 | Tue
Nov 24 | - Sampling and Monte Carlo Integration
| Tutorial 8 |
Wed
Nov 25 | - Sampling and Monte Carlo Integration
|
Thu
Nov 26 | - Course recap [slides]
- Exam info [slides]
|
