Video of the lectures is available via the echo360 portal of the course. A link will be provided on Canvas.
Topics | Reading | Assignments | |
---|---|---|---|
Week 1: August 20-24 | |||
Monday | Course introduction ( slides). | Sections 1.1 and 1.2 in the textbook | |
Wednesday | Course introduction (continued). | Sections 1.1 and 1.2 in the textbook | |
Friday | Course introduction and Jupyter notebooks. | Assignment 1 is available. Due 9/7. | |
Week 2: August 27-31 | |||
Monday | Overview of Numpy ( notebook) and Matplotlib ( notebook). | A tutorial on how to write efficient code using Numpy | |
Wednesday | Linear models and the perceptron algorithm ( slides). | Chapter 1, and Section 3.1 in the textbook | |
Friday | Linear models (continued). Perceptron notebook. | ||
Week 3: September 4-7 | |||
Wednesday | Linear regression ( slides). | Chapter 3.2 | |
Friday | Linear regression (continued). | Chapter 3.2 | Assignment 2 is available. Due 9/21 |
Week 4: September 10-14 | |||
Monday | Logistic regression ( slides). | Chapter 3.3 | |
Wednesday | Logistic regression (continued). | Chapter 3.3 | |
Friday | Overfitting ( slides). | Chapter 2.3,4.1 | |
Week 5: September 17-21 | |||
Monday | Overfitting (continued). Regularization ( slides). | Chapter 4 | |
Wednesday | Regularization (continued). Classifier weights as a function of the regularization parameter ( notebook) | Chapter 4 | |
Friday | Cross validation ( notebook). | Assignment 3 is available. Due 10/5. | |
Week 6: September 24-28 | |||
Monday | Measuring classifier accuracy/error ( slides). Notebook on classifier accuracy/error. | ||
Wednesday | Support vector machines ( slides). Useful resource: A user's guide to support vector machines. | Chapter e-8 | |
Friday | Support vector machines (continued). | Chapter e-8 | |
Week 7: October 1-5 | |||
Monday | A deeper look at SVMs ( slides). Code for the svm demo. | ||
Wednesday | Nonlinear SVMs: kernels ( slides). | Chapter e-8 | |
Friday | Kernels (continued). | Chapter e-8 | Assignment 4 is available. Due 10/19. |
Week 8: October 8-12 | |||
Monday | Classifier evaluation ( slides). | ||
Wednesday | Model selection in scikit-learn notebook. | ||
Friday | Kernels (continued). | ||
Week 9: October 15-19 | |||
Monday | Neural networks ( slides). notebook. | Chapter e-7 | |
Wednesday | Neural networks (continued). | Chapter e-7 | |
Friday | Neural networks (continued). | Chapter e-7 | Project proposals due Nov 3rd. |
Week 10: October 22-26 | |||
Monday | Neural networks (continued). | Chapter e-7 | Assignment 5 is available. Due 11/6 |
Wednesday | Neural networks (continued) (updated slides). | Chapter e-7 | |
Friday | Deep networks ( slides). | Chapter e-7 | |
Week 11: October 29 - November 2 | |||
Monday | PyTorch. tensors and neural networks | Also see the PyTorch tutorials. | |
Wednesday | Convolutional networks. | ||
Friday | Convolutional networks in PyTorch. notebook. | ||
Week 12: November 4 - 9 | |||
Monday | Deep learning: auto-encoders ( slides). Multi-class classification ( slides); a demo of multi-class classification | Chapter e-7 | |
Wednesday | Features: selection and scaling ( slides) | Chapter e-9 | |
Friday | Feature selection (continued) notebook | Chapter e-9 | |
Week 13: November 11 - 16 | |||
Monday | Principal component analysis (PCA) ( slides). notebook | Chapter e-9 | |
Wednesday | Nearest neighbor classification ( slides). | Chapter e-9 | |
Friday | Nearest neighbor classification notebook . | Chapter e-9 | |
Thanksgiving week | |||
Week 14: November 26 - 30 | |||
Monday | Discussion of final report. | Final report due Wednesday Dec 12th | |
Wednesday | Clustering ( slides). notebook | Chapter 10 in introduction to statistical learning | |
Friday | Clustering (continued). | Chapter 10 in introduction to statistical learning | |
Week 15: December 3 - 7 | |||
Monday | Ensemble methods ( slides). notebook | ||
Wednesday | Course summary ( slides). notebook | ||
Friday | Poster session | ||
Week 16 | |||
Wednesday | Submit final reports |