-
Notifications
You must be signed in to change notification settings - Fork 415
sequence.md
The class is taught in the sequence of units below. Of course, students not enrolled in the class are free to browse in any order they wish. Right now, some units are empty. But, more will be added over the course of the class.
Ultimately, most units will have a demo where the concepts are illustrated.
The demos are covered in the class lectures.
Some demos have a component that is done in class.
After the lectures, the students complete a more involved
exercise on a new dataset in the lab at home.
The demos do not generally cover
all topics, since some concepts are left for the students to figure out
for themselves in the labs. Also, as you will observe, the labs are
just empty skeletons with TODO markers that the students fill in.
In addition to the lab, most units have a homework which
focuses on more analytic problems. Students will be
provided the full solutions to the homeworks and labs in class
as well as the lecture notes.
If you are an instructor
and wish copies of the solutions for yourself,
please contact Sundeep Rangan at [email protected].
- Setting up python, jupyter and github
- Introduction to
numpyvectors - Unit 1: Simple linear regression
- More
numpy: Python broadcasting - Unit 2: Multiple linear regression
- Unit 3: Model selection and regularization
- Unit 4: Logistic Regression
- Unit 5: Nonlinear optimization
- Unit 6: Support vector machines
-
Unit 7: Neural networks with Keras and Tensorflow
- Demo 7.1: First neural network in Keras
- Demo 7.2: MNIST neural network classification
- Lab 7: Music instrument classification
- Homework 7: Notes with solved problems [pdf] [Latex]
- Unit 8: Convolutional and deep networks
-
Unit 9: PCA
- Demo 9: PCA eigen-faces
- Lab 9: TBD
- Unit 10: Clustering and EM