| Week | Date | Content | Exercise |
|---|---|---|---|
| 1 | 9/8 | 1. Overview of the course | |
| 2 | 9/15 | 1. Introduction to ML 2. KNN 3. k-means 4. Distance measures | Project proposal (group) (due: 9/28 23:59:59) |
| 3 | 9/22 | 1. Entropy 2. Decision tree | |
| 4 | 9/29 | 1. Matrix derivatives 2. Linear regression and regularization (Lasso, Ridge, Elastic-net) | |
| 5 | 10/6 | No physical class; lecture is given by recorded video Logistic regression and gradient ascent | |
| 6 | 10/13 | 1. Evaluation metrics for binary classification, multi-class classification, and multi-label classification 2. ROC curve vs PR curve | |
| 7 | 10/20 | 1. Entropy, cross-entropy, and KL-divergence 2. Practical concerns on traditional machine learning 3. Ensemble learning | |
| 8 | 10/27 | 1. Gradient boosting machines 2. Linear SVM | 1. Progress report (due: 10/26 23:59:59) 2. Kaggle Competition begins (due: 11/16 23:59:59) |
| 9 | 11/3 | Multi-layer perceptron and backpropgagation | |
| 10 | 11/10 | Convolutional neural network | |
| 11 | 11/17 | 1. Kernel SVM 2. Regularized linear regression and classification 3. Linear SVM with poly-2 terms vs. polynomial kernel SVM | |
| 12 | 11/24 | 1. Recurrent neural network 2. Practical concerns of DNN | |
| 13 | 12/1 | 1. Word2Vec 2. Transformer and Large Language Model | |
| 14 | 12/8 | Decoupled learning by associated learning and SCPL | |
| 15 | 12/15 | No physical class; lecture is given by recorded video LLM alignment, LLM bias, and AI ethics | |
| 16 | 12/22 | Flexible learning week: Explainable AI and AI ethics | Final project (due: 12/21 23:59:59) |