The schedule below represents my current best estimate concerning due dates (and everything else). I am providing this information to give you a general idea of the pace and timing of the class. This schedule will certainly change as the semester progresses.

Unless otherwise noted, all readings are from

Readings followed by (S) are supplemental. You may find them helpful.

WEEK DATE TOPIC READING/VIDEOS OUT IN
1 08-27 Introduction to ML
decision_trees_p_1_2.pdf
CH 1 through "Types of Machine Learning Systems" (p. 3-27) Python Setup
2 09-01 Decision Tree Activity (.pdf) CH 5 (p. 179-193)
Fast Numpy Video
https://scipy-lectures.org/ (1.3.1-1.3.2)


09-03 Numpy Lab Linear Algebra Review (S)
Video (S)
More Videos (S)
PA1
linear_algebra_exercises.pdf

3 09-08 Model selection and cross-validation


09-10 Probability and expectation; bias/variance decomposition


4 09-15 Evaluating classifiers; Exam 1 coverage walkthrough


09-17 EXAM 1


5 09-22 Ensembles: bagging, random forests, boosting


09-24 Naive Bayes

PA2
PA1
6 09-29 Matrix geometry warm-up; linear regression and gradient descent



10-01 Logistic regression, likelihood, cross-entropy


7 10-06 Multi-layer perceptrons and backpropagation


10-08 FALL BREAK


8 10-13 PyTorch fundamentals

PA2
10-15 EXAM 2


9 10-20 Network training: ReLU, initialization, regularization
Poster Project

10-22 Computation graphs and automatic differentiation
PA3

10 10-27 Convolutional networks


10-29 CIFAR-10 lab; poster project orientation


Poster Proposal
11 11-03 Recurrent networks: recurrence to attention


11-05 Transformers

PA3 (11/8)
12 11-10 Transformer activity



11-12 EXAM 3


13 11-17 Principal component analysis


11-19 Nonlinear dimensionality reduction

Poster Bibliography
14 11-24 THANKSGIVING


11-26 THANKSGIVING


15 12-01 Clustering


12-03 Poster studio


Poster Checkpoint
16 12-08 EXAM 4


12-10 Poster peer review and revision


Poster Draft
17 12-17 Poster Session and Presentations