CS 6364_4364 Final Project

Announcements

Goals for this Final Project:

Integrate Knowledge: Apply the full range of algorithms covered in the course.
Code Organization: Structure and document your code in a clear, accessible format.
Research Paper: Develop a high-quality, full-length (12-page) research paper.
Professional Citation: Accurately cite relevant research papers and any external code used.

Document Your Learning: Create a comprehensive file (ML_Algorithms.PDF) that details each model you have studied.
- Include a well-organized table of contents for easy navigation.
- Keep sections for each model structured consistently.
Reflect on Your Knowledge:
- Write a reflection on your current understanding of each machine learning model, focusing on core concepts and their connections.
- Use your own words to explain these concepts, demonstrating comprehension and critical thinking.
Identify and Address Learning Gaps:
- As you study, document any questions or areas of difficulty.
- Note specific challenges or uncertainties to guide future learning and clarify areas needing further review.

For Experiment Papers:
- Examine potential applications of each ML model in your project.
- Evaluate and compare the performance outcomes, using metrics such as accuracy, precision, recall, or computational efficiency. Provide insights into which models perform best and why, considering the project’s unique requirements.
For Review Papers:
- Conduct an in-depth review of recent advancements in each ML algorithm, focusing on applications within the past 3–5 years across diverse fields.
- Summarize key findings, like how CNNs have advanced computer vision, healthcare, and autonomous driving, and critically assess the strengths and limitations of each model.
- Discuss emerging trends such as deep residual networks, attention-based models, or innovative CNN architectures.
- Identify current challenges and propose future directions for ML algorithms to address evolving needs in the field.

For Experiment Papers:
- Submit your complete code implementation, ensuring it includes at least five baseline machine learning algorithms for comparison.
- Provide a clear performance comparison using metrics such as accuracy and F1 score, and briefly explain why your primary approach outperforms or complements the baselines.
For Review Papers:
- Summarize the top five GitHub repositories most relevant to your research questions.
- For each repository, provide a brief description of its purpose, the insights it offers, and how it relates to your review topic. Link these repositories as references in your GitHub submission to illustrate their relevance to your research.
Submission Requirements for All Teams:
- Submit a single, well-organized code file or summary file with a maximum file size of 5 MB.
- Ensure your submission folder includes clear documentation (e.g., a README file) that explains the file structure and content.
- Include a README file with clear documentation: Clearly indicate which parts of the code are your original work and which parts are cited from others, with proper citations.

Finalize the Full-Length Paper:
- Complete your paper according to the conference requirements outlined here.
- Aim for a paper length of 12 pages, ensuring it meets the required range (no fewer than 10 pages and no more than 20 pages).
Share Your Draft:
- Share the Overleaf project with the professor using the Overleaf link-sharing feature instructions here.

Each team should submit a single file on behalf of the entire group. Ensure all team members are CC d on the submission.
Name the file as follows: final_project_lastname1_lastname2.zip
Your submission should include:
1. Your_midterm_submission_order_final_project.PDF, Submit your final HCII-format paper, following the double-blind format guidelines. Ensure it is twelve pages and named in the format e.g., 05_Final_Project.pdf.
2. ML_Algorithms.PDF, Document Your Understanding of all the ML Algorithms.
3. Your code submission should consist of a well-organized folder containing only your code files. Ensure the code is properly documented with clear comments explaining key functions and logic. A README file should be included to provide an overview of the code, instructions for running it, and any dependencies or requirements.
4. Exclude Data Files: Do not include any data files in your submission. If your code relies on specific datasets, provide a link or instructions on how to access the data separately in your README file. Ensure your code is flexible enough to run with external data inputs.

Email the zip file for final project to x.qu@gwu.edu.
Lab assignments are typically released on Fridays and are due the following Thursday.
Final Project is due by Thursday, 12/12 at 11:59 PM (EST)