Schedule
Date | Lecture | Readings | Logistics | |
---|---|---|---|---|
Module 1: Introduction, Representation, and Exact Inference | ||||
1/14 |
Lecture #1
(Eric):
Introduction to GM [ slides (annotated) | video | notes ] |
|
||
1/16 |
Lecture #2
(Eric):
Representation: Directed GMs (BNs) [ slides (annotated) | video | notes ] |
|||
1/21 | No class (MLK day) | |||
1/23 |
Lecture #3
(Eric):
Representation: Undirected GMs (MRFs) [ slides (annotated) | video | notes ] |
|
||
1/28 |
Lecture #4
(Eric):
Exact inference - Elimination - Message passing - Sum product algorithm [ slides (annotated) | video | notes ] |
|
HW1 out (Mon, 1/28) |
|
1/30 |
Lecture #5
(skipped):
Parameter learning in fully observable Bayesian Networks - Generalized Linear Models (GLIMs) - Maximum Likelihood Estimation (MLE) - Markov Models [ slides | video | notes ] |
|
||
2/4 |
Lecture #6
(Maruan):
Parameter Learning of partially observed BN - Mixture models - Hidden Markov Models (HMMs) - The EM algorithm [ slides | video | notes ] |
|
||
2/6 |
Lecture #7
(Eric):
Maximum likelihood learning of undirected GM [ slides (annotated) | video | notes ] |
|
||
2/11 |
Lecture #8
(guest lecture, Kun Zhang @ Department of Philosophy):
Causal discovery and inference [ slides | video | notes ] |
|
||
2/13 |
Lecture #9
(Eric):
Modeling networks - Gaussian graphical models - Ising models [ slides (annotated) | video | notes ] |
|
HW1 due (Wed, 2/13) |
|
2/18 |
Lecture #10
(Eric):
Sequential models - Discrete Hidden State (HMM vs. CRF) - Continuous Hidden State (Kalman Filter) [ slides (annotated) | video | notes ] |
|
||
Module 2: Approximate Inference | ||||
2/20 |
Lecture #11
(Eric):
Approximate Inference: Mean Field (MF) and loopy Belief Propagation (BP) approximations [ slides (annotated) | video | notes ] |
HW2 out (Fri, 2/22) |
||
2/25 |
Lecture #12
(Eric):
Theory of Variational Inference: Inner and Outer Approximations [ slides (annotated) | video | notes ] |
|
||
2/27 |
Lecture #13
(Eric):
Approximate Inference: Monte Carlo and Sequential Monte Carlo methods [ slides (annotated) | video | notes ] |
|
||
3/4 |
Lecture #14
(Eric):
Markov Chain Monte Carlo - Metropolis-Hastings - Hamiltonian Monte Carlo - Langevin Dynamics [ slides (annotated) | video | notes ] |
|
||
Module 3: Deep Learning & Generative Models | ||||
3/6 |
Lecture #15
(Eric):
Statistical and Algorithmic Foundations of Deep Learning - Insight into DL - Connections to GM [ slides | video | notes ] |
|
HW2 due (Mon, 3/11) |
|
3/11 | No classes (Spring break) | |||
3/13 | No classes (Spring break) | |||
3/18 |
Lecture #16
(guest lecture, Zhiting Hu):
Building blocks of DL - RNN and LSTM - CNN, Transformers - Attention mechanisms - (Case studies in NLP) [ slides | video | notes ] |
|
HW3 out (Mon, 3/18) |
|
3/20 |
Lecture #17
(Eric):
Deep generative models (part 1): Overview of the theoretical basis and connections of deep generative models - Wake sleep algorithm - Variational autoencoders - Generative adversarial networks - A unified view of DGM [ slides | video | notes ] |
|
||
3/25 |
Lecture #18
(guest lecture, Zhiting Hu):
Deep generative models (part 2) - GANs and their variations - Normalizing Flows - Integrating domain knowledge in DL [ slides | video | notes ] |
|
||
3/27 |
Lecture #19
(guest lecture, Zhiting Hu):
Case Study: Text Generation - The encoder-decoder framework - Machine translation as conditional generation - Unifying MLE and RL objectives for text generation [ slides | video | notes ] |
|
Midway report due (Fri, 3/29) |
|
Module 4: Reinforcement Learning & Control Through Inference in GM | ||||
4/1 |
Lecture #20
(Maruan):
Sequential decision making (part 1): The framework - Brief introduction to reinforcement learning (RL) - Connections to GM: RL and control as inference - Control via Variational Inference [ slides | video | notes ] |
|
||
4/3 |
Lecture #21
(Maruan):
Sequential decision making (part 2): The algorithms - Intro to RL algorithms: policy gradients and Q-learning - Max-entropy policy gradient - Soft Q-learning [ slides | video | notes ] |
|
HW3 due (Wed, 4/3) |
|
Module 5: Nonparametric methods | ||||
4/8 |
Lecture #22
(Eric):
Bayesian non-parameterics - Dirichlet Process (DP) - Indian Buffet Process (IBP) [ slides | video | notes ] |
|
HW4 out (Mon, 4/8) |
|
4/10 |
Lecture #23
(Maruan):
Bayesian non-parameterics (continued) - Inference in Dirichlet Process (DP) - Hierarchical Dirichlet Process (HDP) - Indian Buffet Process (IBP) [ slides | video | notes ] |
|
||
4/15 |
Lecture #24
(Eric):
Integrative Paradigms of GM: Regularized Bayesian Methods [ slides | video | notes ] |
|
||
4/17 |
Lecture #25
(Eric):
Elements of Spectral & Kernel GMs [ slides | video | notes ] |
|
||
4/22 |
Lecture #26
(Maruan):
Gaussian processes (GPs) and elements of meta-learning - Gaussian Processes (GPs) and kernel functions - (Deep) kernel learning and approximations - Neural Processes (NPs) as an approximation to GPs - Elements of meta-learning [ slides | video | notes ] |
|
||
Module 6: Modular and scalable algorithms and systems | ||||
4/24 |
Lecture #27
(guest lecture, Qirong Ho):
Scalable algorithms and systems for learning, inference, and prediction [ slides | video | notes ] |
|
HW4 due (Mon, 4/24) |
|
4/29 |
Lecture #28
(Eric):
Industialization of AI: standards, modules, building-blocks, and platform [ slides | video | notes ] |
|||
5/1 | Project presentations (TBA) |