CS 6364_4364 Lab 9

Lab 9 is due by Thursday, 11/14 at 11:59 PM (EST)

Announcements

Class participation, Google Folder.
(Back to Course Index Page)

Goals

Goals for this Lab Assignment:

Learn and Implement the CNN (Convolutional Neural Network) Deep Learning Algorithm
Integrate CNN Models into Final Project (If Applicable)

1. Learn and Implement

Develop a solid understanding of CNN architecture, focusing on key components like convolutional layers, pooling, and fully connected layers.
Gain hands-on experience by implementing CNNs for tasks such as image classification or pattern recognition using relevant datasets.
Analyze the performance of your CNN model, focusing on important metrics like accuracy, precision, and recall, and experiment with tuning hyperparameters to optimize results.
Document Your Understanding of the CNN Model in your ML_Algorithms.PDF
- Write a Reflection: Summarize your current understanding of the CNN (Convolutional Neural Network) model. Focus on key concepts such as convolutional layers, pooling layers, activation functions, and how these elements work together to extract features from input data. Explain these concepts in your own words to demonstrate your comprehension. You may also discuss how CNNs are applied in real-world tasks, such as image classification, object detection, or pattern recognition.
- Identify Learning Gaps: As you progress through the material, document any questions or challenges you encounter while learning about CNNs. These could include difficulties with understanding how convolution operations work, challenges in implementing CNNs, or confusion around hyperparameter tuning. Be specific in describing these gaps to help guide future learning, whether through self-study or discussions with peers and instructors. Providing concrete examples of where you struggled (e.g., implementing backpropagation in CNNs) can enhance your understanding.

2. Integrate it into Final Project (If Applicable)

For Experiment Papers: Explore potential use cases for CNN models in your project. Identify specific tasks where CNNs can improve performance or efficiency, such as image recognition, pattern detection, or feature extraction. Implement the CNN algorithm as part of your experiment, and compare its performance with other baseline models. Analyze the outcomes by evaluating metrics such as accuracy, precision, recall, or computational efficiency. Additionally, explore how techniques like data augmentation or transfer learning can further enhance the CNN’s performance in your project.
For Review Papers: Investigate recent advancements in CNN algorithms, focusing on their application in various fields over the past 3–5 years. Summarize key findings, such as how CNN-based models have revolutionized tasks in computer vision, healthcare, autonomous driving, or other industries. Provide a critical analysis of the strengths and limitations of CNN models, discussing trends like deep residual networks, attention-based enhancements, or the use of CNNs in novel architectures. Identify emerging challenges and future directions for CNN research.

3. Submit your code

For Experiment Papers:Submit your current code implementation. In your submission, highlight two to three baseline machine learning algorithms that you have compared with your approach. Include a clear comparison of performance metrics (e.g., accuracy, F1 score) and a brief explanation of why your CNN-based approach outperforms or complements the baselines.
For Review Papers: Summarize at least three GitHub repositories that you found most relevant and helpful to your research questions. For each repository, include a brief description of its purpose, the key insights gained, and how they relate to your review topic. Add these repositories as references to your own GitHub repository, demonstrating how they connect to your research.
Each team should submit one code file containing the code or summaries, with a file size limit of 5 MB or less.
Ensure the folder is well-organized with clear documentation (e.g., a README file explaining the structure and content).

4. Upate Your HCII paper

Begin Expanding to Full-Length Paper: Start extending the abstract into a 12-page full-length paper, which is due as part of your final project.

5. Double-Blind Preparation:

Ensure that both your code and paper are double-blind and ready for peer review. This means:
- For Code: Remove any identifying information, such as author names, affiliations, or comments that could reveal your identity. Use neutral file names and ensure the folder structure does not contain personal or project-specific identifiers.
- For Papers: Ensure that your paper does not include any references to your identity, institution, or any personal acknowledgments. Avoid citing your own previous work in a way that could reveal your identity (e.g., refer to your past work in the third person).

6. Submission Guide

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: lab_9_lastname1_lastname2.zip
Your submission should include:
1. Your_midterm_submission_order_Lab_9.PDF, the final paper draft in double-blind format (e.g., 5th_lab_9.pdf).
2. ML_Algorithms.PDF, Document Your Understanding of the CNN Model.
3. Your 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.

7. Notes

Email the zip file for Lab 9 to x.qu@gwu.edu.
Lab assignments are typically released on Fridays and are due the following Thursday.
Lab 9 is due by Thursday, 11/14 at 11:59 PM (EST)