Welcome!
This virtual online course aims to introduce you to research methods in Deep Learning, with a focus on Computer Vision! This 7-week program will help you develop a research project from start to finish. By the end of the program, you will have created a publication manuscript draft, mastered your presentation skills, and established habits for a fruitful research career!
Program Calendar
Program Components
Project Proposal
Due July 19th
The project proposal should be one paragraph (200-400 words). Your project proposal should describe:- What is the problem that you will be investigating? Why is it interesting?
- What literature will you review to show context and related works?
- What architecture and methods are you proposing? How does your work differ from existing implementations?
- How will you quantitatively and qualitatively evaluate your results?
Project Check-In
Due August 2nd
The project check-in should be between 2-3 pages. The check-in should include:- Introduction that provides context on related works, the structure of your paper, and what novel methods you are suggesting.
- Problem Statement: What is the problem at hand, why is it relavent and important?
- Technical Approach: Summarize your methods and any planned experiments you have to test them.
- Early Results: Provide results for your baseline comparisons and any other preliminary quantitative/qualitative findings.
Final Manuscript Draft
Due August 23rd
The final manuscript should be between 6 - 8 pages and should be structured using this template. The outline of your manuscript is as follows:- Title and Authors
- Abstract: Summarize your work in no more than 300 words.
- Related Work: Review published work and explain the novelty of your methods/results.
- Data: What is the dataset you used, its distribution, size, and other characteristics.
- Methods: Discuss your methods and why it was appropriate for the problem at hand. Diagrams of your figure, including system architecture, mathetmical equations, tables, and other helpful media.
- Experiments: Discuss tests you did for your model. Ablation studies, testing for accuracy, hyperparameter tuning, etc. Graphs and tables illustrating your results are required.
- Conclusion: Give the gist of your findings; highlight what new contributions you have made to the field and discuss real-world applications of your findings.
Video Presentation
Due August 23rd
The final presentation should be a maximum 5 minute video presentation. You can show demos of your model in action, a slide presenation, etc. Make sure to discuss the following points in your presentation:- The problem's importance
- Related Methods in the literature
- Summary of your methods
- Figures/Tables of your results
- High-level implications and applications of your findings