| Group | Title | Slides |
|---|---|---|
| 1 | Predicting the number of replies of a Facebook post | PPTX |
| 2 | Weather forecast | PPTX |
| 3 | Identify and localize COVID-19 abnormalities on chest radiographs | PPTX |
| 4 | Object detection with aerial camera | PPTX |
| 5 | Snake game AI | |
| 6 | Spam or Ham? | PPTX |
| 7 | Using Semantic segmentation on hyperspectral images to predict the landcover | PPTX |
| 8 | Stock Price Prediction | PPTX |
| 9 | Forecasting the adaptability level of the online learning students | PPTX |
| 10 | Effect of obesity on inhibitory control in preadolescents during stop-signal task: an event-related potentials study | PPTX |
| 11 | House price prediction | PPTX |
| 12 | Is your anime wife drawn by NovelAI? | PPTX |
| 13 | What causes car accidents? | PPTX |
| 14 | PM2.5 prediction | PPTX |
| 15 | How do wine components affect quality? | PPTX |
| 16 | Player grading system in table tennis | PPTX |
| 17 | Stock price forecasting with prophet, LSTM, and a hybrid approach | PPTX |
| 18 | Training to become a real Sonic The Hedgehog in a classic Sonic game | PPTX |
| 19 | Heart failure prediction | PPTX |
| 20 | House price prediction | PPTX |
| 21 | (Dropped) | |
| 22 | Using voice to identify whether an indivicual is wearing a mask | PPTX |
| 23 | Image classification and localization using photos taken by UAVs | PPTX |
| 24 | Facial expression recognition | PPTX |
| 25 | Prediction of suspected money laundering transactions | PPTX |
| 26 | Face emotion recognition for behaviour analysis | PPTX |
| 27 | Music genre classification | PPT |
| 28 | (Dropped) | |
| 29 | Stock price prediction | |
| 30 | COVID-19 detection based on the chest X-ray images | PPTX |
| Week | Date | Content | Exercise |
|---|---|---|---|
| 1 | 9/13 | 1. Overview of the course | |
| 2 | 9/20 | 1. Introduction to ML 2. KNN 3. k-means | Exercise 1 (due: 10/3 23:59:59) |
| 3 | 9/27 | 1. Distance measures 2. Entropy 3. Decision tree | |
| 4 | 10/4 | 1. Decision tree 2. Matrix derivatives | |
| 5 | 10/11 | Linear regression and regularization (Lasso, Ridge, Elastic-net) | Exercise 2 (due: 10/24 23:59:59) |
| 6 | 10/18 | 1. Logistic regression and gradient ascent 2. Evaluation metrics for binary classification | |
| 7 | 10/25 | 1. Evaluation metrics for multi-class and multi-label classification 2. ROC curve vs PR curve | Exercise 3 (due: 11/14 23:59:59) |
| 8 | 11/1 | Midterm project proposal presentation | |
| 9 | 11/8 | SVM: linear vs kernel; primal vs dual | |
| 10 | 11/15 | 1. Regularized linear regression and classification 2. Linear SVM with poly-2 terms vs polynomial kernel SVM 3. Practical concerns | |
| 11 | 11/22 | Multi-layer perceptron | |
| 12 | 11/29 | Convolutional neural network | |
| 13 | 12/6 | 1. Convolutional neural network 2. Recurrent neural network | Exercise 4 (due: 12/20 23:59:59) |
| 14 | 12/13 | 1. Associated Learning 2. Recommender systems | |
| 15 | 12/20 | 1. Differentiating regularization weight 2. Factorization Machine and Field-aware Factorization Machine 3. Learning to rank | |
| 16 | 12/27 | Invited talk (Speaker: Prof. Chin-Te Lin @ME, NCU) Pratical concerns and case studies | Final project report (due: 1/2 23:59:59) |
| 17 | 1/3 | Flexible learning week: Field trip to the FESTO lab | |
| 18 | 1/10 | Flexible learning week: Explainable AI and ethics |