Artificial Intellegence /Machine Learning Master's Project
IE7945 • Fall 2024 • Northeastern University • Vancouver
This course offers students a culminating experience to demonstrate proficiency in key concepts learned throughout their programs in core and elective courses. Designed to reinforce concepts in ethics and basic research principles, beyond an emphasis on technical knowledge.
- Term: Fall 2024
- Class: Thursdays, 3:30 PM - 4:30 PM PT
- Location: Vancouver 1426
- Dates: 09/04/2024 – 12/06/2024
- HW Submission: Gradescope
- Q&A Platform: Piazza, please sign up with your northeastern email.
- Course Repository: IE7945 materials
-
Whiteboard: MS Whiteboard
: Overleaf or Visual Studio Code, depending on your team preference.- Code Repository: Github, please register your account, and share with the instructor.
- Project Management: Jira, you will receive an invitation to join the project management tool.
-
Portfolio: Github Pages, optional but encouraged.
- Teaching style: There’s no speed limit
- Instructor: Zhenyuan Lu
- Email:
- Office hours: Thursday 3:30-4:30pm PT
- Guest Lecturer: Xiaozang Li
- Title: Google Cloud Customer Engineer
- Expertise: Cloud Architect
- 10+years experience, ex-amazon
- Guest Lecturer: Jinhui Zhao
- Title: Software Engineer, Tech Lead
- Expertise: Full Stack
- 10+years experience, ex-tiktok/ amazon
- Guest Lecturer: TBD
- Title: TBD
- Expertise: TBD
Tools & Resources
Editors
- Overleaf (Preferred for collaboration, you can log in with your northeastern email)
- Visual Studio Code
Template
- We will use the [CVPR 2025] templates for the paper, please download it to the local and then upload it to Overleaf.
Git Repository
- As this is a group project, we will use Github for version control. Please register your account on [Github]
Project Management
- To understand how to manage the project in industry, we will use We will use [Jira] for sprint planning and tracking . You will receive an invitation to join the project management tool.
Portfolio
- If you are interested in creating a portfolio, you can use [Github Pages], this is optional but encouraged.
Note: before posting any content on github, please consult with your instructor and industry mentor.
Team Projects (Industry Partner)
| Project | Team Members | Industry Partner | Instructor |
|---|---|---|---|
| Clasibot 2.0: Towards Autonomous Bookkeeping | Li Bao, Priya Hiteshkumar Daiya, Haritha Rathnam Kuppala, Suraju Ibiyemi | Classibot.com | Zhenyuan Lu |
| Live Timeless: Health Dashboard & AI Coach | Yuanyuan Chen (She/Her), Ravi Teja Chintalapudi, Maharshi Shukla, Mohammed Rayyan Sami | Live Timeless | Zhenyuan Lu |
Grading (Subject to Change)
- 20% Project Check-ins (Individual):
- Good Execution - 3%, Average - 2%, Poor - 1%, None - 0%
- 10% Project Proposal (Group)
- 30% Panel Review (Group)
- 15% Draft Paper (Introduction, Related Work, Methodology)
- 15% Presentation
- 30% Final Deliverables (Group):
- 15% Full Paper
- 15% Full Presentation
- 10% Exit Interview (Individual)
- Late Submissions: 20% off per day, up to 100%.
Course Schedule
(subject to change)
| Date | Lecture | Content | Logistics | |
|---|---|---|---|---|
| Module 1: How To Start | ||||
| 9/26 |
Introduction and Expectations; Project Management
Instructor: Zhenyuan Lu |
[Submit] Check-In I due 10/03 @ 11:59pm PT |
||
| 10/3 |
Industry in a Nutshell
Guest Lecturer: XiaoZang Li 
Section: Literature Review Instructor: Zhenyuan Lu |
|
[Submit] Check-In II due 10/03 @ 11:59pm PT |
|
| 10/10 |
Industry in a Nutshell II
Guest Lecturer: Jinhui Zhao Section: Introduction and Background Instructor: Zhenyuan Lu |
|
[Submit] Project proposal due extended to 10/13 @ 11:59pm PT |
|
| Module 2: What's Next | ||||
| 10/17 |
Section: How to Organize Related Work and Methodology
Instructor: Zhenyuan Lu |
|
[Submit] Check-In III due 10/17 @ 11:59pm PT |
|
| 10/24 |
Section: Industry in a Nutshell III
Instructor: Zhenyuan Lu |
|
[Submit] Check-In IV Related work and methodology due 10/24 @ 11:59pm PT |
|
| 10/31 |
Panel Review
Instructor: Zhenyuan Lu |
|
Draft paper + Presentation due 10/31 @ 11:59pm PT |
|
| Module 3: Final Stretch | ||||
| 11/7 |
Data Visualization and Concept
|
|
||
| 11/14 |
Research Analysis
|
|
||
| 11/21 |
Discussion and Conclusion
|
|
||
| 11/28 |
Final Deliverables
|
|
Full paper + recorded presentation due 11/28 @ 11:59pm PT |
|
| 12/5 |
Exit Individual Interview
|
|
Interview + Feedback 12/5 @ Class Meeting |
|
| Module: Happy Holidays! | ||||
Expectations
- General: Respectful communication with faculty, staff, industry, and peers. Students should come prepared, engage with materials, and participate actively.
- Accommodations: If you need accommodations (e.g. child care, extra time), please speak with the instructor at the beginning of the course.
- Attendance: Required for all classes. Absences should be communicated via email. Repeated absences will be evaluated by faculty.
- Classroom Conduct: Maintain a civil and respectful environment for discussion. Disagreements must be respectful and based on facts.
- Collaboration and Academic Honesty: Collaboration is encouraged, but students are responsible for their own work. Cite any substantive discussions with peers. Do not copy code or answers from others or online sources.
Grade Scale
Letter grade will be assigned at the end of the semester.
This course does not have any quizzes or exams.
Take care of yourself
Eating healthy food, having regular exercises, avoiding alcohol and drugs, getting adequate sleep and taking time to relax. This will help you achieve your goals and tame stress.
If you have difficulty to keep up with any materials or homework for personal reasons please let me know early. If you or your friends/classmates who appears to be struggling, or having trouble coping with stress. We strongly encourage you to seek support at the We Care program at NEU. At Northeastern, a student is never alone when struggling with a demanding situation.
Policies
Plagiarism, cheating, and any form of unauthorized collaboration will not be tolerated and will be handled in accordance with University policies described in the Student Handbook. For additional information on Northeastern University’s Academic Integrity Policy
AI Tools
AI tools, including ChatGPT, are encouraged to assist in your work. However, your unique intellectual contributions are essential. Use AI to enhance, not replace, your efforts.
Title IX
Northeastern prohibits discrimination based on sex or gender identity. If you or someone you know is affected by sexual harassment or violence, confidential support is available through University Health and Counseling Services.
Student Feedback
Please use the TRACE system to provide feedback at the end of the course. The instructor may also seek feedback halfway through the semester.
Accommodations for Students with Disabilities
If you have a disability, I encourage you to contact Disability Resource Center to register and request the accommodations. Also please discuss your needs with me as early in the semester as possible.
Course Outcomes
- Exhibit proficiency in the design, implementation, and testing of software.
- Apply algorithmic and theoretical computer science principles to solve computing problems from a variety of application areas.
- Research and apply ethical considerations when solving computing problems.
- Read, discuss, and extract key ideas from research papers published at top-tier computing conferences.
- Demonstrate the conceptual and methodical competence to present research in the computing field.
Course Requirements
- Attendance is required for:
- All scheduled classes
- All team meetings (on/off-campus)
- All meetings with project stakeholders (on/off-campus)
- Individual Contributions:
- Each student must contribute equally and demonstrate skill development in all competency areas listed in the course outcomes.
- Individual contributions must demonstrate reasonable quality and application of technology.
- Students who do not contribute significantly may receive an adjusted grade.
- Students who miss the Exit Interview and Showcase Day will receive a failing grade.
Individual Project (Special Case - Not For Team Project Members)
| Project | Materials | Individual | Instructor |
|---|---|---|---|
| Contrastive Learning, Self-supervsied Learning | References | Rida Khan | Zhenyuan Lu |
Only for individual projects, Contrastive Learning:
- Review 3 key papers,
- Suggested: 2020: A Simple Framework for Contrastive Learning of Visual Representations
- Choose a research topic (e.g., image classification, time series, etc.) regarding contrastive learning.
- due 10/3 @ 4:30pm PT
- Write a two-page summary for each paper (total 6 pages) using Overleaf and [CVPR 2025] template
- due 10/10 @ 11:59pm PT submit to Gradescope:
- Paper overview
- Key contributions
- Methodology
- Results and conclusions
- due 10/10 @ 11:59pm PT submit to Gradescope:
- Decide one of the following project directions (due 10/17 @ 11:59pm PT):
- Survey paper: Review at least 20 papers.
- Benchmark with coding: Implement models and use datasets from the papers to compare results.
- Specific research paper: Formulate a unique research question and conduct a study.
- Write the final paper based on the chosen direction.
- Prepare and deliver a project presentation.
- All other tasks should be the same as the group project team members.