| Week | Date | Content | Exercise |
|---|---|---|---|
| 1 | 9/10 | 1. Overview of the course | |
| 2 | 9/17 | Holiday (mid autumn festival) | |
| 3 | 9/24 | 1. Introduction to ML 2. KNN 3. k-means 4. Distance measures | Project proposal (group) (due: 9/30 23:59:59) |
| 4 | 10/1 | 1. Entropy 2. Decision tree | |
| 5 | 10/8 | 1. Decision tree 2. Matrix derivatives | |
| 6 | 10/15 | Linear regression and regularization (Lasso, Ridge, Elastic-net) | |
| 7 | 10/22 | 1. Logistic regression and gradient ascent 2. Evaluation metrics for binary classification, multi-class classification, and multi-label classification | |
| 8 | 10/29 | 1. ROC curve vs PR curve 2. Entropy, cross-entropy, and KL-divergence 3. Practical concerns on traditional machine learning | 1. Progress report (due: 10/28 23:59:59) 2. Kaggle Competition 1 begins (due: 11/18 23:59:59) |
| 9 | 11/5 | Ensemble learning | |
| 10 | 11/12 | 1. Gradient boosting machines 2. Linear SVM | |
| 11 | 11/19 | 1. Kernel SVM 2. Regularized linear regression and classification 3. Linear SVM with poly-2 terms vs. polynomial kernel SVM | Kaggle Competition 2 begins (due: 12/9 23:59:59) |
| 12 | 11/26 | 1. Multi-layer perceptron 2. Convolutional neural network | |
| 13 | 12/3 | 1. Convolutional neural network 2. Recurrent neural network | |
| 14 | 12/10 | Word2Vec, Prod2Vec, Behavior2Vec, and contrastive learning | |
| 15 | 12/17 | Transformer and Large Language Model | |
| 16 | 12/24 | Associated learning | Final project due: 12/30 23:59:59 |
| 17 | 12/31 | Flexible learning week:Invited talk (speaker will be announced) | |
| 18 | 1/7 | Flexible learning week: Explainable AI and ethics |