Topic Schedule
| # | Day | Date | Topic | Reading | Homework |
| 01 | Wed. | 15 Jan. | Class introduction | Syllabus | |
| 02 | Wed. | 22 Jan. | Linear regression | James, et al., Introduction to Statistical Learning, ch. 1, 2.1–2.2 [link] | Homework 01 out |
| 03 | Mon. | 27 Jan. | Linear and polynomial regression | James, et al., Introduction to Statistical Learning, ch. 3.1 [link] | |
| 04 | Wed. | 29 Jan. | Gradient descent (and gradient ascent);
error, over-fitting, and cross-validation |
Deep Learning book, Section 4.3 (gradient descent) | Homework 01 due |
| 05 | Mon. | 03 Feb. | Linear classification: the perceptron model | Reading on linear methods
(on Piazza)
Linear separator interactive Perceptron learning interactive |
|
| 06 | Wed. | 05 Feb. | Evaluating ML algorithms | Zheng, Evaluating ML Models (O'Reilly, free PDF), chapters 1–2 | |
| 07 | Mon. | 10 Feb. | Logistic regression | James, et al., Introduction to Statistical Learning, 4.1–4.3 | |
| 08 | Wed. | 12 Feb. | Other classifiers: decision trees | Daumé, A Course in Machine Learning, chapter 1 (link) | Homework 02 due |
| 09 | Wed. | 19 Feb. | Boosting classifiers | Reading on boosting
(on Piazza) Paper by Viola & Jones (2004) |
|
| 10 | Thu. | 20 Feb. | Feature engineering | James, et al., Introduction to Statistical Learning, ch. 6.1 [link] | |
| 11 | Mon. | 24 Feb. | Clustering, I | Daumé, CIML, chapter 3 (link) | |
| 12 | Wed. | 26 Feb. | Clustering, II | Reading on nonparametric methods (on Piazza) | Homework 03 due |
| 13 | Mon. | 02 Mar. | Support vector machines (SVMs) and kernel functions, I | James, et al., Introduction to Statistical Learning, 9.1–9.4 | |
| 14 | Wed. | 04 Mar. | SVMs and kernels, II | ||
| 15 | Mon. | 09 Mar. | Exam review | Project 01 due | |
| 16 | Wed. | 11 Mar. | In-class midterm exam | ||
| 17 | Mon. | 23 Mar. | No class (spring break extended) | ||
| 18 | Wed. | 25 Mar. | Semester logistics going forward; introduction to neural nets (Live class on Zoom) |
||
| 19 | Mon. | 30 Mar. | Introduction to neural networks (No live class) |
Goodfellow, et al., Deep Learning, 6.1–6.2.2.3 (pp. 164–184) | |
| 20 | Wed. | 01 Apr. | Training neural networks (Live class on Zoom) |
Goodfellow, et al., Deep Learning, 6.5.1–6.5.8 (pp. 200–217) | 21 | Mon. | 06 Apr. | Backpropagation; tuning hyper-parameters (No live class) |
Backpropagation walkthrough |
| 22 | Wed. | 08 Apr. | Convolutional neural networks (Live class on Zoom) |
Goodfellow, et al., Deep Learning, 9.1–9.3 (pp. 326–329) | |
| 23 | Mon. | 13 Apr. | Markov decision processes (MDPs) | Sutton and Barto, Reinforcement Learning, chap. 3, 4.1–4.3 | Homework 04 due |
| 24 | Wed. | 15 Apr. | Dynamic programming & reinforcement learning | Sutton and Barto, Reinforcement Learning, 6.1–6.5 | |
| 25 | Wed. | 22 Apr. | Reinforcement learning, II | ||
| 26 | Mon. | 27 Apr. | Semester wrap-up | Project 02 due | |
| Fri. | 08 May. | Final paper due (no final exam) |