| Week | Date | Content | Exercise |
|---|---|---|---|
| 1 | 9/9 | Overview of the course | |
| 2 | 9/16 | 1. Probabilistic learning 2. Probability (joint distribution, marginal distribution, conditional distribution) 3. Factorization |
|
| 3 | 9/23 | 1. Bayesian network 2. D-separation |
Exercise 1 (due: 10/13 23:59:59) |
| 4 | 9/30 | UPDATED: 颱風假 |
|
| 5 | 10/7 | Exact inference by variable elimination TA session: Introduction to Python and popular scientific libraries in Python |
|
| 6 | 10/14 | No class (Make-up class will be announced) |
|
| 7 | 10/21 | Exact inference by variable elimination | |
| 8 | 10/28 | Exact inference by message passing | Exercise 2 (due: 11/11 14:00) |
| 9 | 11/4 | 1. Exponential family and conjugate prior 2. Midterm review |
|
| 10 | 11/11 | Midterm exam | |
| 11 | 11/18 | 1. Midterm review 2. Exponential family and conjugate prior 3. EM algorithm |
|
| 12 | 11/25 | Markov chain, Gibbs Sampling, and Metropolis-Hastings | Exercise 3 (due: 12/9 14:00:00) |
| 13 | 12/2 | Markov Chain Monte Carlo (MCMC) and Latent Dirichlet Allocation (LDA) | |
| 14 | 12/9 | Variational inference | |
| 15 | 12/16 | 1. Scaling variational inference 2. Invited talk (柯維然先生)：Introduction to Deep Probabilistic Programming with Pyro (暫定) |
Exercise 4 (due: 12/30 14:00) |
| 16 | 12/23 | Bayesian linear regression | |
| 17 | 12/30 | 1. Gaussian process 2. Bayesian optimization 3. Final exam review |
|
| 18 | 1/6 | Final exam |