Video of the lectures is available via the echo360 portal of the course. A link is provided on Canvas and Piazza.
Topics | Reading | Assignments | |
---|---|---|---|
Week 1: August 23,25 | |||
Tuesday | Course introduction ( slides). | Sections 1.1 and 1.2 in the textbook | |
Thursday | Course introduction (continued). | Sections 1.1 and 1.2 in the textbook | Assignment 1 is available. |
Week 2: August 30, Sept 1 | |||
Tuesday | Linear models ( slides). Short intro to LaTex and python [ notes ]. | Chapter 1, and Section 3.1 in the textbook | |
Thursday | Linear models and the perceptron algorithm (cont). | Chapter 1, and Section 3.1 in the textbook | Assignment 2 is available. |
Week 3: September 6,8 | |||
Tuesday | code for the perceptron. Linear regression ( slides). | Chapter 3.2 | |
Thursday | Logistic regression ( slides). | Chapter 3.3 | |
Week 4: September 13,15 | |||
Tuesday | Overfitting ( slides) | Chapters 2.3,4.1 | |
Thursday | Regularization and model selection ( slides) | Chapter 4 | |
Week 5: September 20,22 | |||
Tuesday | Model selection and cross validation (continued). Code for cross validation in scikit-learn | Chapter 4 | Assignment 3 is available. |
Thursday | Discussion of classifier evaluation and metrics for classifier accuracy; here's the code for computing/plotting ROC curves. Short intro to large margin classification ( slides) | Chapter e-8 | |
Week 6: September 27,29 | |||
Tuesday | Large margin classification: support vector machines ( slides) | Chapter e-8 | |
Thursday | The dual for the hard margin and soft margin SVM ( slides); svm demo; Expressing SVMs in terms of error + regularization ( slides) | Chapter e-8 | |
Week 7: October 4,7 | |||
Tuesday | SVMs for unbalanced data ( slides) Nonlinear classification with kernels ( slides) | Chapter e-8 | Assignment 4 is available. |
Thursday | Kernels (continued); model selection using grid search | Chapter e-8 | |
Week 8: October 11,13 | |||
Tuesday | Model selection ( slides). Multi-class classification ( slides), a demo of multi-class classification | Chapter 4.3.3 | |
Thursday | Neural networks ( slides) | Chapter e-7 | |
Week 9: October 18,20 | |||
Tuesday | Neural networks (continued); neural network demo | Chapter e-7 | Assignment 5 is available. |
Thursday | Neural networks (continued); deep learning ( slides) | Chapter e-7 | |
Week 10: October 25,27 | |||
Tuesday | Deep learning (continued) | Chapter e-7 | |
Thursday | Theano. Features ( slides) | Chapter e-9 | |
Week 11: November 1,3 | |||
Tuesday | Feature selection ( slides); feature selection demo. | Introduction to Variable and Feature Selection. | |
Thursday | Principal components analysis (PCA) ( slides) demo of pca | Chapter e-9 | Assignment 6 is available. |
Week 12: November 8,10 | |||
Tuesday | Nearest neighbor methods ( slides); demo. | Chapter e-6 | |
Thursday | Clustering ( slides) kmeans demo | Chapter 10 in introduction to statistical learning | |
Week 13: November 15,17 | |||
Tuesday | Naive Bayes classification ( slides); demo. | ||
Thursday | Intro to computational learning theory ( slides) | Chapter 1.3 in the textbook | |
Thanksgiving break | |||
Week 14: November 29, December 1 | |||
Tuesday | The VC dimension ( slides); Least squares regression revisited ( slides) | Chapter 2.1, 2.2 in the textbook | |
Thursday | Ensemble models ( slides); demo. | ||
Week 15: December 6,8 | |||
Tuesday | Course summary ( slides) | ||
Thursday | Poster session | ||
Week 16 | |||
Tuesday | Submit final reports |