AIST4010/ESTR4140: Foundation of applied deep learning-Spring 2023

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

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 (, SHB-106. Office hour: 3pm-5pm, Friday

Time and location

Monday: 2:30pm-4:15pm, ERB-703.
Thursday: 2:30pm-3:15pm, ERB-804.
Thursday: 3:30pm-4:15pm, ERB-804. Tutorial
Thursday: 5:30pm-6:15pm, ERB-406. ESTR-4140


Mainly onsite. Slides will be available the day before the lecture day. We will also provide the Zoom session.



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.


Bonus (up to 2.5%): 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. Register here:

Open-book quiz policy

The quiz is open-booked.


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.


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


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 27th Jan. After that, the Google sheet will be closed. Here are some good scribing examples from another course.


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 (6%), a mid-term report (7%), a final report (17%) and give a presentation (17%). Both the lecturer (90%) and the students (10%) 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

Lec Date Location Topic Slides/Video Notes Reading Important dates (All due at 11:59 pm)
1 Jan 9 (Mon) ERB-703 Introduction Lec-1      
2 Jan 12 (Thu) ERB-804 ML review Lec-2   Data mining book, D2L, Colab, Kaggle A0 posted
3 Jan 16 (Mon) ERB-703 LR/NN Lec-3   D2L, Universal approximation theorem  
4 Jan 19 (Thu) ERB-804 Backpropagation Lec-4   D2L, Universal approximation theorem, Chain rule, Subgradient  
- Jan 23 (Mon) - - - - - Lunar New Year Vacation
- Jan 26 (Thu) - - - - - Lunar New Year Vacation, Scribing preference, 27 Jan
5 Jan 30 (Mon) ERB-703 CNN       A0 due, A1 posted
6 Feb 2 (Thu) ERB-804 Overfitting        
7 Feb 6 (Mon) ERB-703 CNN++        
8 Feb 9 (Thu) ERB-804 CNN++        
9 Feb 13 (Mon) ERB-703 Optimization        
10 Feb 16 (Thu) ERB-804 Optimization       A1-paper due
11 Feb 20 (Mon) ERB-703 Loss function       Project proposal
12 Feb 23 (Thu) ERB-804 Text processing       A1-Kaggle due, A2 posted
13 Feb 27 (Mon) ERB-703 RNN        
14 Mar 2 (Thu) ERB-804 RNN++        
- Mar 6 (Mon) - - - - - Reading Week
- Mar 9 (Thu) - - - - - Reading Week
15 Mar 13 (Mon) ERB-703 RNN++       A2-paper due, A3 posted
16 Mar 16 (Thu) ERB-804 Attention       Project M-report
17 Mar 20 (Mon) ERB-703 BERT       A2-Kaggle due
18 Mar 23 (Thu) ERB-804 NLP        
19 Mar 27 (Mon) ERB-703 Graph        
20 Mar 30 (Thu) ERB-804 GNN       A3-paper due
21 Apr 3 (Mon) ERB-703 GAN       A3-Kaggle due
22 Apr 6 (Thu) ERB-804 Generative        
- Apr 10 (Mon) - - - - - Easter Monday
23 Apr 13 (Thu) ERB-804 Course summary       Participation Quiz
24 Apr 17 (Mon) ERB-703 Project pres        
25 Apr 20 (Thu) ERB-804 Project pres       Project report