Course goals: In this course we aim to provide students with data analysis tools to solve machine learning problems. Based on feedback from prior courses (such as courses taught at Qualcomm and UCSD), these topics cover in depth and practical methodologies that are taught in data science, data mining, and machine learning courses. The primary focus is on supervised learning algorithms with in depth understanding of linear models (since they are so foundational). We also cover ensemble and decision tree models (random forests and boosting) since they are widely used in industrial applications. If time permits, we also cover multi-layer perceptrons for students to understand future deep learning courses.
Suggested background: linear algebra, basic optimization, probability and statistics (as covered here: https://docs.google.com/document/d/1RA6pUvrqtI2IuXPZSuN7aVxIJVqNUxDW6SgCyhu7zIg/edit)
Course lectures are presented in as Jupyter Notebooks.