CS291K - Special Topics in Deep Learning home | schedule



Abstract: This is a graduate-level research course on deep learning.  We will discuss/present newest and important publications in deep learning, specifically Transformer-based techniques in the areas of knowledge base, question answering, conversational AI, natural language processing and multimodal learning.

Each student is expected to read papers before lecture, write paper reviews, present papers,  and complete a research-quality course project (e.g., implement an existing algorithm or solve a new problem creatively using deep learning. One team could have two students. ).  Projects that simply apply CNN, LSTM or Transformers are not encouraged.

Prerequisites: Neural network building experience or successfully finished an introductory deep learning course.

Enrollment Code: 60665 Instructor: Prof. Xifeng Yan

Time: Tuesday/Thursday 11:00- 12:50pm, Location: PHELP 3526   Office Hour:  Monday 12:00-1:00pm,  Wed  11-12:00pm,  Henley Hall 2017

TA: N/A.  Research Project Coordinator:  Shiyang Li, Jing Qian, Hong Wang, Zekun Li

Grading: Your grade will be derived from paper review (15%),  paper presentation/midterm quiz (15%), project presentation (15%), project quality (40%), project proposal (5%), project report (10%)  + Extra Credit 10% per additional paper presentation volunteered by you.

Paper Reading: You are required to read every paper carefully before lecture.

Paper Review: Find two deep learning papers that are not presented in lecture but highly related to your project, and write a detailed 2-page review.  Your review shall include your understanding of the work, discuss its strength and weakness, and mostly important, propose new ideas to improve it.   The review is due on May 3.  A review will be graded by the quality of the paper (20%) and the quality of your review (80%).

Text Books (not required, but you'd better read it)

Deep Learning, An MIT Press book, Ian Goodfellow and Yoshua Bengio and Aaron Courville