Note: 2pp = 2 slides per page (portrait), 4pp = 4 slides per page (landscape).
| Week | Monday | Wednesday | Friday |
|---|---|---|---|
| Week #1 Jan 7 - 11 |
Lecture: Overview (2pp, 4pp), Directed Graphical Models (Introduction) (2pp, 4pp) Assignment #1 out |
Lecture: Directed Graphical Models (Reasoning Patterns, Independencies) (2pp, 4pp) Reading: Section 3.2.1.2, 3.2.2, 3.2.3 |
Lecture: Directed Graphical Models (D-separation) (2pp, 4pp) Reading: Section 3.3 |
| Week #2 Jan 14 - 18 |
Lecture: Directed Graphical Models (I-equivalences, Distributions and Graphs) (2pp, 4pp) Genie example (HMM.xdsl) Assignment #2 Assignment #1 due Reading: Section 3.4 (up to 3.4.3) |
Lecture: Undirected Graphical Models (Introduction to Markov Networks) (2pp, 4pp) Reading: 4.1, 4.2 |
Lecture: Undirected Graphical Models (Independencies) (2pp, 4pp) Reading: 4.3 |
| Week #3 Jan 21 - 25 |
No class (MLK day) | Lecture: Undirected Graphical Models (Chordal graphs) (2pp, 4pp) Reading: 4.4 Assignment #2 due Assignment #3 out |
Lecture: Boltzman Machines (2pp, 4pp) |
| Week #4 Jan 28 - Feb 1 |
Lecture: Exact Inference (Enumeration, Variable Elimination) (2pp, 4pp) Reading: Chapter 9.1-9.3 |
Lecture: Exact Inference (Variable Elimination) (2pp, 4pp) Reading: Chapter 9.3 Assignment #3 due |
Lecture: Exact Inference (Complexity of Variable Elimination) (2pp, 4pp) Reading: 9.3 |
| Week #5 Feb 4 - 8 |
Lecture: Exact Inference (Message Passing) (2pp, 4pp) Reading: 10.1, 10.2 Practice Midterm, Practice Midterm Solutions |
Lecture: Exact Inference (Message Passing 2) (2pp, 4pp) | No Class |
| Week #6 Feb 11 - 15 |
Midterm | Lecture: Approximate Inference (Sampling, Likelihood Weighting) (2pp, 4pp) | Midterms returned Project proposal due |
| Week #7 Feb 18 - 22 |
Lecture: Approximate Inference 2 (Importance Sampling) (2pp, 4pp) Assignment #4 out Reading: 12.2 |
Lecture: Monte Carlo Markov Chain 1 (2pp, 4pp) Reading: Chapter 12.3 |
Lecture: Monte Carlo Markov Chain 2 (2pp, 4pp) Reading: Chapter 12.3 |
| Week #8 Feb 25 - Mar 1 |
Snow day | Snow day | Lecture: Parameter Learning 1 (2pp, 4pp) Assignment #4 due Project Checkpoint |
| Week #9 Mar 4 - 8 |
Lecture: Parameter Learning 2 (2pp, 4pp) | Lecture: Structure Learning (Chow Liu Trees) (2pp, 4pp) Assignment #5 out | Lecture: Structure Learning (Constraint-Based Approaches) (2pp, 4pp) Reading: Chapter 3.4.3, 18.1-18.2 |
| Week #10 Mar 11 - 15 |
Lecture: Structure Learning (Structure Scoring) (2pp, 4pp) Reading: 18.3, 18.4.3 | Lecture: Variational Inference (2pp, 4pp) Assignment #5 due |
Consultation session for projects |
Projects are due Mar 20, 2019 at 5:00 pm. Please slide the writeup under my door (or email the pdf) and submit the code via the TEACH handin.