AIST4010: Foundation of applied deep learning-Spring 2022

[Pre-course survey, Piazza, Scribing preference, Logistics, Course schedule and materials, Assignments]

Course description

This course covers how to use deep learning techniques to resolve real-life computational problems, handling different kinds of data. We start the course by introducing the problem-solving paradigm with deep learning: data preparation, building the model, training the model, model evaluation, and hyper-parameter searching. Then, we fill in the details in the paradigm. Regarding the deep learning models, we will go from the simplest linear regression model, towards the relatively complicated models. To handle various data types, that is, the structured data, images, text, sequences, signals, and graphs, in our daily life, we would cover CNN/ResNet, RNN/LSTM, Attention, and GNN models. In addition to the above paradigm, we will also cover the commonly used techniques to handle overfitting. We would briefly go through the generative models, VAE, and GAN, at the end of this course.

Teaching team

Lecturer: Yu LI (liyuATcse.cuhk.edu.hk), SHB-106. Office hour: 3pm-5pm, Friday
TA: Licheng ZONG (lczongATlink.cuhk.edu.hk), SHB-1026. Office hour: 2:30pm-4:30pm, Tuesday

Time and location

Monday: 2:30pm-4pm, ERB-712.
Thursday: 2:30pm-3:15pm, YIA-503.
Thursday: 3:30pm-4:15pm, YIA-503. Tutorial

Format

Mixed. Slides will be available the day before the lecture day. Video recordings will be available after the lecture.

Logistics

Communications

Blackboard is the main software to manage the course, and grading will be through blackboard. We will use Piazza (AIST4010) for discussion. You can ask questions through Piazza, even anonymously. For a personal matter, please use the private post to the instructor and the TA. You are also very welcomed to send emails to the instructor and TAs.

Grading

• Homework (42%): One non-grading assignment (6%, set up the environment) and three grading homework (12%+12%+12%).
• Scribing (6%): Grading scribing. Summarize one of the lectures. Submit it within one week after the course. Each student should do at least one lecture. You can sign for at most two, for additional 1%.
• In-class quiz (5%): One in-class quizzes. The questions will be simple. Mainly for checking the participation. The exact date are in the below schedule.
• Midterm (15%, Cancelled): A grading midterm exam. One bonus question (1%).
• Project (47%): A grading project. You should submit a proposal (6%), a mid-term report (7%), a final report (17%) and give a presentation (17%).

Bonus (up to 2.5%): One bonus question in Midterm (1%). One additional scribing: 1%. Pre-course survey + Post-lecture survey: 0.3% for each, and the maximum is 1.5%. I do encourage you to complete all of them so that to let me know your feedback and adjust the course accordingly. Send your names to the TA.

Open-book quiz and exam policy

All exams and quiz are open-book. You are allowed to take any paper-based materials. However, no phone or computer is allowed. Other communication tools are also not allowed. Discussion is not allowed.

Assignment

Half of them will be fixed-answer questions while half of them will be Kaggle competition. The last Kaggle competition is optional. If you participate in that one, you final score of the Kaggle part will be the highest two out of the three.

• You need to compete with your classmates.
• The TA will set up a baseline using linear regression and simple deep learning. If you are better than the baseline, you can be above 60%. If you are better than the deep learning baseline, you can be above 80%.
• The final score of each student will be based on the ranking. The first one gets 100%, and the last one above the deep learning baseline gets 80%. Scores will be interpolated linearly.

Programming

Python or any other you are familiar with. For python, we suggest you to use Colab.

Scribing

Please sign Scribing preference. We should have at least one student for each lecture. We may adjust the assignment if necessary. Notice that your note and scribing will be posted online, for others reference. You can choose to remove your name or not. Deadline for signing the scribing: 11:59 pm on 17th Jan. After that, the Google sheet will be closed.

Projects

You can choose to do the project individually or team-up. However, for the team-up project, we will have higher requirement and the project should target at publication. Moreover, the contribution of each student and the workload split should be defined clearly at the beginning of the project. Please discuss with me if you want to do serious team-up project. You should submit a proposal (5%), a mid-term report (6%), a final report (16%) and give a presentation (16%). Both the lecturer (80%) and the students (20%) will be the markers.

Late days

Each student will have 6 late days to turn in assignments, which can be used on A1, A2, A3, project proposal, and project M-report. They cannot be used on the project final report and the scribing note. A maximum of 2 late days can be used for each assignment. Grades will be deducted by 25% for each additional late day.

Post-lecture survey

Deadline for each survey: 11:59pm on the day before the next lecture. We do this because I could have time to answer the questions you mentioned in the survey. Please fill 1 in the Google sheet: Survey results, once you have finished one survey. Usually, we will trust the 1s you fill in the Google sheet. But we will check the things in detail if the number of survey forms we received and the number of 1s on the Google sheet is not consistent.

Course schedule and materials

Assignments

• Assignment 1: Image
• Assignment 2: Text/sequence
• Assignment 3: Graph