Advanced Machine Learning

Course Description: Covers advanced topics in machine learning. Focuses on probabilistic graphical models, inference and learning algorithms, and their connections to deep learning. This is a PhD level course with emphasis on mathematical principles as well as practical know-how.

The course syllabus will continuously be updated with methods from state-of-the-art research.

Course Details:

• Lecturer: Professor Qi (Rose) Yu (roseyu@northeastern.edu)
• TA: Clara De Paolis (depaoliskaluza.m@husky.neu.edu)
• Time: 11:45 am - 1:25 pm Monday, Thursday
• Location: Forsyth Building 202
• Piazza: piazza.com/northeastern/spring2020/cs7140
• Office Hours: 462 WVH Thu 3:00 pm - 4:00 pm/by appointment

Prerequisite:

• CS 6140 Machine Learning
• Familiar with linear algebra, statistics, optimization
• Proficient at programming in Python

Course Assessment:

• 40 % homework (10% x 4)
• 40 % project
• 15 % paper discussion
• 5 % lecture scribe

NOTES: For students who need computing resources for the class project, we recommend you to look into Google Colab or AWS educate program.

Course Syllabus

Course Material

• Lecture 1 Lecture 2 Lecture 3 Lecture 4 Lecture 5 Lecture 6 Lecture 7 Lecture 8 Lecture 9 Lecture 10 Lecture 11 Lecture 12 Lecture 13
• Scribe 2 Scribe 3 Scribe 4 Scribe 5 Scribe 6 Scribe 7 Scribe 8 Scribe 9 Scribe 10 Scribe 11 Scribe 12 Scribe 13

Final Project

• Latex Template
• Suggested Topic

References (required):

• [1] Information Theory, Inference, and Learning Algorithms
• [2] Probabilistic Graphical Models: Principles and Techniques
• [3] Deep Learning Book

Additional References (optional):

• [4] Graphical Models, Exponential Families and Variational Inference
• [5] The Elements of Statistical Learning
• [6] Graphical Model Course