| Event Type | Date | Description | Readings | Course Materials |
|---|---|---|---|---|
| Lecture 1 | Wednesday Jan 10 |
What is machine learning? Course overview and an orientation to the major branches of machine learning: unsupervised, supervised, and reinforcement learning |
None | [slides] |
| No class | Monday Jan 15 |
Martin Luther King, Jr. Day | ||
| Snow Day | Wednesday Jan 17 |
Snow Day | ||
| Lecture 2 | Monday Jan 22 |
Core tools I Python (numpy, matplotlib, and pandas) and Jupyter notebooks (markdown, code execution, plotting, creating slides, and creating PDFs) |
ISL Ch. 1 + 2.1 | [slides] [demo slides] |
| Lecture 3 | Wednesday Jan 24 |
Core tools II Code management best practices and Git version control |
ISL Intro of 2.2 and 2.2.1 | [slides] |
| Deliverable | Monday Jan 29 |
Assignment #1 Due | [assignment] | |
| Lecture 4 | Monday Jan 29 |
End-to-end Supervised learning We will walk through an example of a supervised machine learning problem from problem formation to performance evaluation and implementation, demonstrating the various components we will explore throughout the semester |
ISL 2.2.2 | [slides] |
| Lecture 5 | Wednesday Jan 31 |
How flexible should my algorithms be: the bias-variance tradeoff K-nearest neighbors classification and the bias-variance tradeoff |
ISL 2.2.3 | [slides] |
| Lecture 6 | Monday Feb 5 |
Linear Models I Simple linear regression, multiple linear regression, measuring error, model fitting and least squares, comparing linear regression and classification |
ISL Intro of 3 and 3.1 | [slides] |
| Lecture 7 | Wednesday Feb 7 |
Linear Models II Nonlinear transformations of predictors, cost/loss functions, selecting parameters through gradient descent. |
ISL 3.2 | [slides] |
| Deliverable | Monday Feb 12 |
Assignment #2 Due | [assignment] | |
| Lecture 8 | Monday Feb 12 |
Evaluating performance I Choosing the right mode: accuracy vs speed vs interpretability; metrics for supervised learning performance evaluation: types of errors, receiver operating characteristics curves, confusion matrices |
ISL 3.3 and 3.5 | [slides] |
| Lecture 9 | Wednesday Feb 14 |
Evaluating performance II Resampling techniques: training, testing, and validation datasets, the importance of ensuring representative resampling, and cross validation |
ISL 4.1, 4.2, 4.3 | [slides] |
| Lecture 10 | Monday Feb 19 |
Decision theory How to operate supervised learning algorithms in practice |
ISL 4.5 | [slides] |
| Lecture 11 | Wednesday Feb 21 |
Reducing overfit Model and feature selection; Occam’s razor; Subset selection; L1 (ridge), L2 (LASSO), and elastic net regularization. |
ISL 4.4 | [slides] |
| Lecture 12 | Monday Feb 26 |
Dimensionality reduction The Curse of Dimensionality and principal components analysis (PCA) |
ISL 5.1, 5.2 |
[slides]
|
| Deliverable | Wednesday Feb 28 |
End of Kaggle Competition | [kaggle competition] | |
| Lecture 13 | Wednesday Feb 28 |
Clustering I K-means and introduction to clustering |
ISL 6.1 |
[slides]
|
| Deliverable | Monday Mar 5 |
Assignment #3 Due | [assignment] | |
| Lecture 14 | Monday Mar 5 |
Clustering I (continued) From K-means to Gaussian mixture model clustering and Expectation Maximization |
ISL 6.2 | [slides] |
| Deliverable | Wednesday Mar 7 |
Kaggle Competition Reports Due | [kaggle report] | |
| Lecture 15 | Wednesday Mar 7 |
Clustering II Hierarchical clustering, DBSCAN, and spectral clustering |
ISL 6.3 | [slides] |
| Deliverable | Friday Mar 9 |
Kaggle Team Peer Evaluation | [peer evaluation] | |
| No class | Mar 12-16 | Spring break week | ||
| Lecture 16 | Monday Mar 19 |
Other models for classification Linear discriminant analysis and naïve Bayes |
None | [slides] |
| Lecture 17 | Wednesday Mar 21 |
Ensemble learning From decision trees to random forests: bagging, bootstrapping, and boosting |
ISL 6.4 | [slides] |
| Lecture 18 | Monday Mar 26 |
Neural networks I How a neural network works |
ISL 7.1-7.4 | [slides] |
| Deliverable | Wed Mar 28 |
Final Project Proposal | [final project] | |
| Lecture 19 | Wednesday Mar 28 |
Neural networks II Backpropagation and deep learning |
ISL 7.5-7.7 | [slides] |
| Lecture 20 | Monday Apr 2 |
Reinforcement Learning I Formulating the reinforcement learning problem |
ISL 8.1 | [slides] |
| Lecture 21 | Wednesday Apr 4 |
Reinforcement Learning II Policy and value functions, rewards, and introduction to Markov processes |
ISL 8.2 | [slides] |
| Deliverable | Monday Apr 9 |
Assignment #4 Due | [assignment] | |
| Lecture 22 | Monday Apr 9 |
Reinforcement Learning III From Markov Chains to Markov Decision Processes (MDPs) |
ISL 9.1-9.2 | [slides] |
| Lecture 23 | Wednesday Apr 11 |
Reinforcement Learning IV Finding optimal policies through policy iteration, value iteration, and Monte Carlo methods |
ISL 9.3-9.4 | [slides] |
| Lecture 24 | Monday Apr 16 |
Kernel Smoothing Non-parametric methods including kernel density estimation, kernel regression, and local regression |
ISL 10.1-10.2.2 | [slides] |
| Lecture 25 | Wednesday Apr 18 |
Kernel Methods Introducing Kernel machines via the kernel perceptron, maximum margin classifiers, and support vector machines |
ISL 10.2.3-10.2.4 | [slides] |
| Deliverable | Friday Apr 20 |
Assignment #5 Due | [assignment] | |
| Lecture 26 | Monday Apr 23 |
State-of-the-art machine learning and applications Cutting-edge applications and techniques: ideas on where the field is heading |
ISL 10.3 | [slides] |
| Deliverable | Wednesday Apr 25 |
Final project video showcase and competition The grand finale of the semester in which all of the videos you produced will be shown to the class |
[final project] | |
| Deliverable | Thursday Apr 26 |
Final Report | [final project] | |
| Deliverable | Friday Apr 27 |
Kaggle Team Peer Evaluation | [peer evaluation] |