| Group | Title | Slides |
|---|---|---|
| 1 | Deep Neural Networks applied to the Search for Extra-Terrestrial Intelligence | ODP |
| 2 | Video Comprehension via Bullet Screen | PPTX |
| 3 | Enterovirus prediction: Forecasting an outbreak with AI | PPTX |
| 4 | Gender and age prediction using profile image | PPTX |
| 5 | NBA Game Win/Loss Prediction | PPTX |
| 6 | Earthquake prediction | PPTX |
| 7 | Classifying the sentences in the abstracts of the papers | PPTX |
| 8 | Gender prediction using profile images from mixture sources | PPTX |
| 9 | Rapid identification of antibiotics susceptibility based on matrix-assisted laser desorption ionization-time of flight mass spectrometry | PPTX |
| 10 | Mobile phone price prediction | PPTX |
| 11 | Automatic garbage sorter | PPTX |
| 12 | Willingness to purchase insurance | PPTX |
| 13 | Negative News Events for Financial Distress Prediction | PPTX |
| 14 | Identify faces and distances from camera and sentiment analysis from text | PPTX |
| 15 | Cryogenic electron microscopy 2D classification with CNN | |
| 16 | Music Tracks and Features Analysis | PPTX |
| 17 | Air Pollution Device Malfunction Detection | PPTX |
| 18 | NYSE Investment strategies backtest and One day ahead stock price prediction | PPTX |
| 19 | An analysis on the causalities of car accident | PPTX |
| 20 | My life consultant - predicting whether a student is suitable for IT industry | PPTX |
| 21 | Google Play rating prediction | PPTX |
| 22 | Football game result predictor | PPTX |
| 23 | Automatic news title generation | PPTX |
| 24 | Matching salesman with customers | PPTX |
| 25 | Heart disease prediction | PPTX |
| 26 | House price prediction | PPTX |
| 27 | Red wine quality prediction | PPTX |
| Week | Date | Content | Exercise |
|---|---|---|---|
| 1 | 9/10 | 1. Overview of the course | |
| 2 | 9/17 | 1. Introduction to ML 2. KNN 3. k-means | Exercise 1 (due: 9/23 23:59:59) |
| 3 | 9/24 | 1. Distance measures 2. Entropy 3. Decision tree | |
| 4 | 10/1 | 1. Decision tree 2. Linear regression and gradient descent TA session: Introduction to Python and popular scientific libraries in Python | Exercise 2 (due: 10/14 23:59:59) |
| 5 | 10/8 | 1. Linear regression and regularization (Lasso, Ridge, Elastic-net) 2. Matrix derivatives | |
| 6 | 10/15 | No class (Make-up class will be announced) | |
| 7 | 10/22 | 1. Evaluation metrics for regression problem 2. Logistic regression and gradient ascent 3. Precision, recall, ROC curve, and other measures | |
| 8 | 10/29 | SVM | Exercise 3 (due: 11/11 23:59:59) |
| 9 | 11/5 | Midterm project proposal presentation | |
| 10 | 11/12 | 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 | 11/19 | 1. Practical considerations 2. Recommender systems 3. Differentiating regularization weights | |
| 12 | 11/26 | Ensemble methods | |
| 13 | 12/3 | Deep neural network | Exercise 4 (due: 12/16 23:59:59) |
| 14 | 12/10 | Convolutional neural network | |
| 15 | 12/17 | Recurrent neural network | |
| 16 | 12/24 | Word embedding and graph embedding | |
| 17 | 12/31 | Final project presentation | |
| 18 | 1/7 | Final wrap-up | Final project report (due: 1/7 23:59:59) |