CS-GY 9223: Assignments - Fall 2025
Course Assignments
⚠️ Important Notice: Assignment details, due dates, and requirements are tentative and subject to revision during the semester. Final assignments may differ from those listed below. Students will be notified of any changes via course announcements.
This page contains all assignment materials for CS-GY 9223: Visualization for Machine Learning.
Assignment Overview
The course includes six exercises designed to build your skills in visualization for machine learning, progressing from basic critique to advanced interactive systems. Each assignment builds upon previous work and prepares you for the final project.
Exercise Schedule
| Assignment | Released | Due Date | Weight | Topic |
|---|---|---|---|---|
| Exercise 1 | Week 2 (Sept 8) | Sept 15 | 5% | Visualization Critique |
| Exercise 2 | Week 3 (Sept 15) | Sept 22 | 5% | Color Palette Design |
| Exercise 3 | Week 4 (Sept 22) | Sept 29 | 8.33% | Model Assessment Visualization |
| Exercise 4 | Week 5 (Sept 29) | Oct 6 | 8.33% | Interactive Explainer |
| Exercise 5 | Week 8 (Oct 20) | Oct 27 | 8.33% | Dimensionality Reduction Dashboard |
| Exercise 6 | Week 9 (Oct 27) | Nov 3 | 8.33% | Deep Learning Visualization |
Total Exercise Weight: 43.32% of final grade
Assignment Guidelines
Submission Requirements
- Code Repository: All assignments must be submitted via GitHub with proper documentation
- Live Demo: Working demonstration hosted on GitHub Pages or similar platform
- Written Report: 2-3 page technical report describing your approach and findings
- Video Presentation: 3-5 minute video walkthrough of your visualization
Technical Requirements
- JavaScript/D3.js: Primary implementation language
- Web Standards: Use HTML5, CSS3, SVG for visualization
- Data Formats: Support for CSV, JSON data loading
- Browser Compatibility: Must work in modern browsers (Chrome, Firefox, Safari)
- Responsive Design: Visualizations should adapt to different screen sizes
Evaluation Criteria
Each assignment will be graded on:
- Technical Implementation (40%)
- Code quality and organization
- Proper use of D3.js and web technologies
- Functionality and performance
- Visual Design (30%)
- Aesthetic quality and visual appeal
- Effective use of color, typography, and layout
- Accessibility considerations
- Machine Learning Integration (20%)
- Appropriate visualization of ML concepts
- Accuracy in representing model behavior
- Insightful analysis and interpretation
- Documentation (10%)
- Clear written explanations
- Proper code documentation
- Quality of video presentation
Late Policy
- 20% deduction per day for late submissions
- Maximum 5 days late before assignment receives zero points
- Extensions only granted for documented emergencies
Assignment Descriptions
Exercise 1: Visualization Critique
Due: September 15, 2025
Develop critical analysis skills by evaluating existing machine learning visualizations. Practice identifying strengths, weaknesses, and potential improvements in current visualization tools.
Exercise 2: Color Palette Design
Due: September 22, 2025
Create perceptually-based color palettes for machine learning data visualization. Implement color scales that are both aesthetically pleasing and functionally effective for different data types.
Exercise 3: Model Assessment Visualization
Due: September 29, 2025
Build an interactive dashboard for evaluating machine learning model performance. Visualize classification metrics, confusion matrices, and ROC curves with comparative analysis capabilities.
Exercise 4: Interactive Explainer
Due: October 6, 2025
Develop an interactive system for explaining black-box machine learning models using techniques like LIME or SHAP. Create intuitive interfaces for model interpretation.
Exercise 5: Dimensionality Reduction Dashboard
Due: October 27, 2025
Implement an interactive visualization system for exploring high-dimensional data through dimensionality reduction techniques (PCA, t-SNE, UMAP).
Exercise 6: Deep Learning Visualization
Due: November 3, 2025
Create visualizations for understanding deep neural networks, including network architecture displays, activation patterns, and training dynamics.
Resources
Technical Resources
Dataset Sources
Visualization Inspiration
Getting Help
- Discord: Primary communication channel for assignment questions
- Office Hours: Posted on Discord, available for one-on-one help
- Peer Discussion: Encouraged, but cite any collaboration in submissions
- Online Resources: Permitted with proper attribution
Academic Integrity
All work must be your own. You may discuss assignments with classmates and use online resources, but:
- Cite all sources and collaborations in your submission
- Do not copy code directly from others
- Be able to explain any solution you submit
- Use AI tools responsibly - disclose any AI assistance used
Violations of academic integrity will result in assignment failure and may lead to course failure.
This page will be updated throughout the semester. Check back regularly for clarifications and additional resources.