Class Project Information
Teams
The final project will be done in teams of 3 people. Please fill in the team assignment form before November 11.
Important Milestones
| Deadline | Task |
| November 11 | Submit group assigment |
| November 29 | Submit project proposal |
| December 6 | Team meeting with course staff |
| December 25 | Submit poster PDF file (Submission will be closed at 11:59am) |
| December 27 | Poster session |
| January 3 | Submit final report |
Proposal: The proposal should be no more than one page (single-space, excluding references). It should briefly describe the topic, background, related work, problem and proposed method of your project.
Meeting with course staff: After submitting the proposal, please arrange a meeting with the instructor or one of the TAs get feedback on the project proposal.
Poster Presentation: We will hold a poster session to showcase your project on the final week. Each group need to submit a poster in PDF format of A0-size to Web Learning before December 25. You will present your work in our final class on December 27.
Final Report: Each group should submit a written report in a single PDF document with at most 4 pages. All related materials, such as source code, should also be provided.
Project Topic
You may choose any topic you are interested in (such as your research area) as long as it pertains to the topics of this class. You are encouraged to explore advanced machine learning techniques and novel data-driven applications. While we encourage interdisciplinary projects, the main focus should be about applying and understanding learning methods rather than the data collection and hardware design process.
Usually, your project will fall into one of the following categories:
Application: use machine learning to solve a specific problem, e.g.
AI applications such as computer vision, NLP, speech recognition, etc
Information processing for physical systems, such as energy, material and optics
Algorithm: develop a machine learning method that has better performance, e.g.
Improve the robustness of an algorithm under noisy data
Make a machine learning method more efficient
Theory: theoretical problems, e.g.
Theoretical analysis of a specific learning algorithm regarding its generalization, consistency, or stability properties
Use existing theoretical concepts to create efficient learning algorithms
A good project will showcase your ability to clearly define a problem (with practical or theoretical importance), demonstate the motivation and technical details of your method, and conduct meaningful evaluation and analysis.
Grading
The final project will count for 25% of your final grade. It will be graded on a scale of 100 points, which include:
Proposal: 15 points
Discussion with class staff: 5 points
Final poster: 25 points
Poster session participation: 5 points
Final report grade: 50 points
Sample Posters, Projects from Previous Years
Poster
Learning Relative Depth Guidance for Human Pose Transfer, Lihan Zhang and Ciyu Ruan
Text-Guided Zero-Shot Audio Style Transfer, Yiran Wang
Depth Restoration for Hand-Held Transparent Object, Ran Yu, Liguang Ruan
Report
Beyond Aggregation: Efficient Federated Model Consolidation with Heterogeneity-Adaptive Weights Diffusion, Jiaqi Li, Siqi Ping
A Transformer-Based Multimodal Classification Network for Smart Tire, Tong Wu, Jiahao Li
IFP: Filter Pruning via Information Flow for Deep Neural Networks Acceleration Chi Xu
Common Pitfalls
Insufficient contribution (e.g. Simply run the code of existing models on some benchmark datasets): Try to come up with at least one novel contribution in any of the three catogries discussed in the Topics section. Or consider a more challenging problem scenario.
Topic is too broad or too ambitious: reduce the project scope
Project relies heavily on external factors (e.g. data collection, hardware equipment) : be sure to have your data ready at the start of the project. Have backup plan (e.g. alternative datasets/tasks) when external requirements can not be met by the time you submit your proposal.