Note: This schedule is a rough approximation and subject to change. Reading chapters are from the textbooks unless mentioned otherwise. Currently we have two textbooks. ISLR- Introduction to statistical learning with applications in R ACML- A course in machine learning
| Week | Date | Reading | Topic | Slides | Assignments |
|---|---|---|---|---|---|
| 1 | Jan. 13 | Machine Learning Intro., KNN | slides | ||
| Jan. 15 | ISLR 3.1, 3.2 | Linear Regression | slides | ||
| Jan. 17 | Hands-on: EDA | notebooks | HW1 out | ||
| 2 | Jan. 20 | No class: MLK | |||
| Jan. 22 | ISLR 4.3 | Logistic regression | slides | ||
| Jan. 24 | ISLR 6.2.1-6.2.3, 5.1 | Techniques to improve training | slides | ||
| 3 | Jan. 27 | ISLR 8.1 | Decision Tree 1 | slides | |
| Jan. 29 | ISLR 8.1 | Decision Tree 2 | slides | ||
| Jan. 31 | Hands-on | HW1 due, HW2 out | |||
| 4 | Feb. 3 | ISLR 8.3.3 | Ensemble methods 1: Bagging | slides | |
| Feb. 5 | ISLR 8.3.4 | Ensemble methods 2: Boosting | slides | ||
| Feb. 7 | Kaggle mini comp 1: regression challenge | ||||
| 5 | Feb. 10 | ISLR 9.1, 9.2 | SVM 1 | slides | |
| Feb. 12 | ISLR 9.3-9.5 | SVM 2 | slides | mini comp 1 closes | |
| Feb. 14 | Hands-on | ||||
| 6 | Feb. 17 | ACML ch4 | Neural Network 1 (perceptron) | slides | HW2 due |
| Feb. 19 | midterm review | ||||
| Feb. 21 | Midterm 1 | ||||
| 7 | Feb. 24 | deeplearningbook Ch.6.1-6.4 | Neural Network 2 (training perceptron, ANN design parameters), demo: intro to Keras | slides | HW3 out |
| Feb. 26 | deeplearningbook Ch.6.5, 8.3 | Back Propagation, Stochastic Gradient Descent | slides | ||
| Feb. 28 | deeplearningbookCh.8.3, 8.5, 8.7.1 | More optimization algorithms, Training tricks, Kaggle mini comp 2: classification challenge | slides | ||
| 8 | Mar. 2 | ISLR 10.1, 10.2, 6.3 | Unsupervised Learning 1: Dimensionality Reduction | slides | |
| Mar. 4 | ISLR 10.3 | Unsupervised Learning 2: Clustering | slides | ||
| Mar. 6 | Hands-on | mini comp 2 closes, HW4 out | |||
| 9 | Mar. 9 | MMDS Ch.9.1-9.3 | Recommender System | slides | |
| Mar. 11 | MMDS Ch.9.4-9.6, paper | Matrix Factorization | slides | HW3 due | |
| Mar. 13 | |||||
| 10 | Mar. 16 | NMF applications-Topic modeling | notebook, whiteboard | ||
| Mar. 18 | deeplearningbook Ch. 9.1-9.3, 9.10, 9.11 | CNN 1: Basics | slides | ||
| Mar. 20 | resource: Stanford's 231n course has great resources on (convolutional) neural networks. | CNN 2: Architectures & Training | slides | ||
| 11 | Mar. 23 | No class: Spring Break | |||
| Mar. 25 | No class: Spring Break | ||||
| Mar. 27 | No class: Spring Break | ||||
| 12 | Mar. 30 | review | |||
| Apr. 1 | review | ||||
| Apr. 3 | Midterm 2 | ||||
| 13 | Apr. 6 | CNN 3: Advanced topic | slides | ||
| Apr. 8 | deeplearningbook Ch. 14.1-14.5 | Unsupervised Neural Networks | notebook whiteboard | HW4 due, HW5 out | |
| Apr.10 | Kaggle mini comp 4: Image classification, Keras mini tutorial | project announcement | |||
| 14 | Apr. 13 | deeplearningbook Ch. 10.1, 10.2 | RNN 1 | slides | |
| Apr. 15 | RNN 2 | mini comp 4 closes | |||
| Apr. 17 | Hands-on | ||||
| 15 | Apr.20 | project discussion | Team formation deadline | ||
| Apr. 22 | project discussion | ||||
| Apr. 24 | project discussion | HW5 due | |||
| 16 | Apr. 27 | project discussion | |||
| Apr. 29 | project discussion | ||||
| May. 1 | no class | ||||
| Finals week | May. 3 | Project deliverable due |