This is a tentative schedule only. As the course progresses, the schedule will be adjusted.
| Lecture | Date | Topic | Readings (textbooks) |
|---|---|---|---|
| 1 | Jan 10 | Introduction to Machine Learning (slides) | |
| 2 | Jan 12 | K-nearest neighbours (slides, annotated slides) | [D] Sec. 7.6, [B] Sec. 3.1 |
| 3 | Jan 17 | Linear regression (slides, annotated slides) | [D] Sec 7.6, [B] Sec 3.1 |
| 4 | Jan 19 | Statistical learning (slides, annotated slides) | [B] Sec 1.2, [M] Sec. 2.1, 2.3 |
| 5 | Jan 24 | Linear regression by maximum likelihood, maximum a posteriori, Bayesian learning (slides, annotated slides) | [B] Sections 3.1 – 3.3 |
| 6 | Jan 26 | Mixture of Gaussians (slides, annotated slides) | [B] Sections 4.2 |
| Jan 27 | Assignment 1 due (11:59 pm) | ||
| 7 | Jan 31 | Logistic regression, generalized linear models (slides, annotated slides) | [B] Sec. 4.3 |
| 8 | Feb 2 | Perceptrons, single layer neural networks (slides, annotated slides) | [D] Chapt. 4, [B] Sec. 4.1.7, 5.1, |
| 9 | Feb 7 | Multi-layer neural networks, backpropagation (slides, annotated slides) | [ZLLS] Chap. 5, [D] Chapt. 10, [B] Sec. 5.2, 5.3 |
| 10 | Feb 9 | Kernel methods (slides, annotated slides) | [D] Chap. 11 [B] Sec. 6.1, 6.2 |
| Feb 10 | Assignment 2 due (11:59 pm) | ||
| 11 | Feb 14 | Deep neural networks (slides, annotated slides) | [ZLLS] Chap. 5, [GBC] Chap. 6, 7, 8 |
| 12 | Feb 16 | Convolutional neural networks (slides, annotated slides) | [ZLLS] Chap. 7, Sec. 8.6, [GBC] Chap. 9 |
| 13 | Feb 28 | Gaussian Processes (slides, annotated slides) | [ZLLS] Chapt. 18, [B] Section 6.4 |
| 14 | Mar 2 | Hidden Markov models (slides, annotated slides) | [B] Sec. 13.1-13.2 |
| Mar 3 | Assignment 3 due (11:59 pm) | ||
| 15 | Mar 7 | Recurrent neural networks (slides, annotated slides) | [ZLLS] Chapt. 9, [GBC] Chap. 10 |
| Mar 8 | CS680 Grad Project Proposal due (11:59 pm) | ||
| 16 | Mar 9 | Attention, Transformers and Structured State Space Sequence (S4) (slides, annotated slides) | [ZLLS] Chapt. 11 |
| 17 | Mar 14 | Graph Neural Networks (slides, annotated slides) | https://en.wikipedia.org/wiki/Graph_neural_network Zhou, Jie, Ganqu Cui, Shengding Hu, Zhengyan Zhang, Cheng Yang, Zhiyuan Liu, Lifeng Wang, Changcheng Li, and Maosong Sun. "Graph neural networks: A review of methods and applications." AI open 1 (2020): 57-81. |
| 18 | Mar 16 | Autoencoders (slides, annotated slides) | [GBC] Chap. 20 |
| Mar 17 | Assignment 4 due (11:59 pm) | ||
| 19 | Mar 21 | Generative networks (variational autoencoders and generative adversarial networks) (slides, annotated slides) | [ZLLS] Chapt. 20, [GBC] Chap. 20 |
| 20 | Mar 23 | Normalizing Flows (slides, annotated slides) | [GBC] Sec. 20.10.7 |
| 21 | Mar 28 | Diffusion Models (slides, annotated slides) | Steins (2022) Diffusion Models Clearly Explained Steins (2022) Stable Diffusion Clearly Explained |
| 22 | Mar 30 | Ensemble learning: bagging and boosting (slides, annotated slides) | [M] Sec. 18.2-18.5, [B] Chap. 14, [D] Chap. 11 |
| Mar 31 | Assignment 5 due (11:59 pm) | ||
| 23 | Apr 4 | Gradient boosting, bagging, decision forests (slides, annotated slides) | [M] Sec. 18.2-18.5, [B] Chap. 14, [D] Chap. 13 |
| 24 | Apr 6 | Support Vector Machines (slides, annotated slides) | [B] Sec. 7.1, [D] Sec. 11.5-11.6, [M] Sec. 14.5 |
| Apr 17 | CS480 Undergrad Competition Report and CS680 Grad Project Report due (11:59 pm) | ||