Lecture Time:
Tuesday and Thursday, 11am-12:20pm, COA B26
Hybrid: In-person and online via Zoom.
TA:
Divyansh Srivastava (ddivyansh@ucsd.edu)
Yucheng Mao (yum038@ucsd.edu)
Text Books:
This course is self-contained and we will make the course slides available online, as well as various useful links.
Office Hours:
Zhuowen Tu: Tuesday (CSB 107 12:30pm-1:30pm), Tuesday (8:00pm-9:00pm, zoom only), Thursday (CSB 107 12:30pm-1:30pm)
Yucheng Mao: Wednesday (CSB 107 11:00am-1:00pm)
Divyansh Srivastava: Friday (CSB 107 11:00am-1:00pm)
Course Description:
This course is an advanced course that follows the basic Machine Learning methods, in particular along the line of supervised approaches. Advanced and new machine learning methods will be discussed and studied. We will go through some popular topics in machine learning covering:
(1) Multi-class and multi-label classification, (2) Structural prediction (Structural SVM, Conditional random fields), (3) Hidden Markov models, (4) Recurrent neural networks, (5) Semi-supervised learning and weakly-supervised learning, (6) Compressed sensing, sparsity and low-rank, (7) Self-supervised learning, (8) Generative AI
Prerequisites:
COGS 118A, or CSE151A, or CGOS181, or consent from the instructor.
Grading policy:
Assignments (five): 50% (dropping the lowest HW; note that the total points on the HWs will be capped and the bonus credit will only be used to help with the lost points in the assignments)
Midterm: 25%
Final project: 25%
Bonus point: 3% (Classroom participation, Piazza, final project)
Late penalty policy: a 5% deduction will be applied for the first day past due, followed by 10% everyday afterwards.