Lecture Time:
Tuesday and Thursday, 2pm-3:20pm, CSB 001
Study Sections:
A01 W 9:00a-9:50a RWAC
A02 W 10:00a-10:50a RWAC
A03 W 11:00a-11:50a RWAC
A04 W 12:00p-12:50p RWAC
TA:
Zheng Ding (zhding@ucsd.edu)
Xiang Zhang (xiz102@ucsd.edu)
Text Books:
This course is self-contained and we will make the course slides available online, as well as various useful links.
https://d2l.ai/
Office Hours:
Zhuowen Tu: Tuesday (CSB 107 3:20pm-3:50pm, Zoom: 7:00pm-8:00pm), Thursday (CSB 107 3:20pm-3:50pm)
Zheng Ding
Xiang Zhang
Office hours during finals week:
Zhuowen Tu: 10:30am-11:30am Monday (03/20), Tuesday (03/21) (Zoom only, Class Zoom link). , 9:30-10:30 Wednesday (03/22)
Zheng Ding: 7:00pm-8:00pm Tuesday(3/21), 8:30pm-9:30pm Wednesday(3/22) and 8:00pm-9:00pm Thursday(3/23) (zoom: https://ucsd.zoom.us/j/99855001852)
Xiang Zhang: 2:00pm-3:00pm on Tuesday(3/21), and Wednesday(3/22), and 11:00am-12:00pm on Thursday (3/23) (zoom: https://ucsd.zoom.us/j/96432027701)
Websites:
Course website (Syllabus, Slide links, Homework links, ...)
Piazza (For posting homework assignments, lecture slides, questions, answers, announcements, polls, ..)
Gradesope (For submitting your homework assignments)
Canvas (Lecture videos, midterm, )
Deep Learning Resources
Deep Learning (Ian Goodfellow and Yoshua Bengio and Aaron Courville)
Neural Networks for Machine Learning (Geoffrey Hinton)
http://cs231n.stanford.edu/
Course Description:
Recent developments in deep neural networks approaches have led to a significant boost to state-of-the-art learning systems in a wide range of domains including machine learning, robotics, perception, computer vision, artificial intelligence, speech recognition, neural computation, medical imaging, bio-informatics, computational linguistics, and social data analysis. This course will cover the basics about neural networks, as well as recent developments in deep learning including deep belief nets, convolutional neural networks, recurrent neural networks, long-short term memory, and reinforcement learning. We will study details of the deep learning architectures with a focus on learning end-to-end models for these tasks, particularly image classification. Students will learn hands-on skills to do cutting-edge research by implementing, training and debugging neural networks.
Grading policy:
Assignments: 50% (the lowest score out of 5 assignments will be dropped).
Midterm: 25%
Final project: 25%
Bonus point: 3% (Piazza, final project)
Late policy: 5% reduction for the first day and 10% reduction afterwards for every extra day past due for the homework assignments and the final project.