Below is the sequence of topics used in the class. Of course, students not enrolled in the class are free to browse in any order they wish. Right now, we have very little material. But, more will be added over the course of the class.
Ultimately, each topic will have a demo where the concepts are illustrated.
The demos are covered in the class lectures. After the lectures, the students complete a similar
exercise on a new dataset in the lab at home. Note 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. Students will be
provided the full solutions in class. 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 - Simple linear regression
- Demo: Understanding automobile mpg
- Lab: Boston housing data. To be completed by the student.
- More
numpy: Python broadcasting - Multiple linear regression
- Demo: Predicting glucose levels
- Lab: Calibrating robot dynamics To be completed by the student.
- Model selection and regularization
- Logistic Regression
- Demo: Breast cancer diagnosis via logistic regression
- Lab: Genetic analysis of Down's syndrome in mice To be completed by the student.
Items to be added over the course of this semester:
- Support Vector Machines (SVMs)
- Introduction to Tensorflow
- Neural networks
- Convolutional neural networks
- PCA
- Clustering and EM