| Group | Title | Slides |
|---|---|---|
| 1 | Improving rare words representations | |
| 2 | Rain forecast based on weather photos | PPTX |
| 3 | Rapid identification of acinetobacter nosocomialis antibiotic susceptibility based on matrix-assisted laser desorption ionization-time of flight mass spectrometry | PPTX |
| 4 | Effectiveness of input data in sound classification task | PPTX |
| 5 | Sentiment analysis of movie review | PPTX |
| 6 | How bad are you? | PPTX |
| 7 | Recipes classification | PPTX |
| 8 | Birds' bones and living habits | PPTX |
| 9 | Stock price prediction | PPTX |
| 10 | NBA Players' Salary Prediction | PPTX |
| 11 | Chang Gung 3D face similarity recognition | PPTX |
| 12 | Credit Card Fraud Detection | PPT |
| 13 | An implementation of gradient boosting classifier for voice-based parkinson's disease identification | PPTX |
| 14 | House prices prediction | PPTX |
| 15 | Using MALDI-TOF MS for resistance/susceptible prediction | PPTX |
| 16 | Netflix visualizations, recommendation system | PPTX |
| 17 | Prediction and analysis on salaries of nba players | PPTX |
| 18 | Drug abuse EKG detect | PPTX |
| 19 | Answer correctness prediction | PPTX |
| 20 | Weather forecast | PPTX |
| 21 | Natural language inference | PPTX |
| 22 | House price prediction | PPTX |
| 23 | Chord estimation | PPTX |
| Week | Date | Content | Exercise |
|---|---|---|---|
| 1 | 9/15 | 1. Overview of the course | |
| 2 | 9/22 | 1. Introduction to ML 2. KNN 3. k-means | Exercise 1 (due: 9/28 23:59:59) |
| 3 | 9/29 | 1. Distance measures 2. Entropy 3. Decision tree | |
| 4 | 10/6 | 1. Decision tree 2. Matrix derivatives | Exercise 2 (due: 10/19 23:59:59) |
| 5 | 10/13 | Linear regression and regularization (Lasso, Ridge, Elastic-net) TA session: Introduction to Python and popular scientific libraries in Python | |
| 6 | 10/20 | 1. Linear regression and regularization (Lasso, Ridge, Elastic-net) 2. Evaluation metrics for regression problem | Exercise 3 (due: 11/2 23:59:59) |
| 7 | 10/27 | 1. Logistic regression and gradient ascent 2. Precision, recall, ROC curve, and other measures | |
| 8 | 11/3 | SVM | |
| 9 | 11/10 | Midterm project proposal presentation | |
| 10 | 11/17 | 1. Regularized linear regression and classification 2. Linear SVM with poly-2 terms vs Polynomial Kernel SVM 3. Factorization Machine and Field-aware Factorization Machine | |
| 11 | 11/24 | 1. Practical considerations 2. Recommender systems | |
| 12 | 12/1 | 1. Recommender systems 2. Differentiating regularization weights 3. Ensemble methods: bagging, boosting (Adaboost, gradient boosting), stacking, XGBoost | Exercise 4 (due: 12/14 23:59:59) |
| 13 | 12/8 | Deep neural network | |
| 14 | 12/15 | Convolutional neural network | |
| 15 | 12/22 | 1. Associated Learning 2. Recurrent neural network | |
| 16 | 12/29 | 1. Attention model 2. Word embedding and graph embedding | |
| 17 | 1/5 | Final project presentation | |
| 18 | 1/12 | Final wrap-up | Final project report (due: 1/11 23:59:59) |