Course Description: Deep learning is showing amazing promise for data science and AI. The course goes in depth on selected topics and methods within deep learning and their applications, including methods to model complex spatiotemporal data, composing graphical models and neural networks for structured representations, recent advances in the theoretical and systems aspects of deep learning, techniques for making deep learning robust to adversarial manipulation, as well as explaining black-box deep learning models to enhance their transparency. It assumes that students already have a basic understanding of deep learning. Examples of relevant applications include intelligent transportation, sports analytics, robotics, and health care.

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: Rui Wang (wang.rui4@husky.neu.edu)
• Time: 11:45 am - 1:25 pm MR
• Location: Snell Library 011
• Piazza: piazza.com/northeastern/spring2019/cs7180
• Office Hours: 2:00 pm - 3:00 pm Tuesday, location: Snell Library 045

Prerequisite:

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

Course Assessment:

• 60% project
• 25 % reading/programming assignments
• 15% class participation (including presenting papers in class)

NOTES: For students who need computing resources for the class project, we recommend you to look into AWS educate program for students. You’ll get 100 dollar’s worth of sign up credit.

Course Syllabus

Final Project [Latex Template]

• Suggested Topic [Topics]

References:

• Deep Learning Book
• Deep Learning Course (Coursera)
• Recurrent Neural Network
• The Elements of Statistical Learning
• Pattern Recognition and Machine Learning