CS-GY 9223: Course Schedule - Fall 2025

Weekly Schedule

⚠️ Important: This schedule is tentative and may be updated during the semester. Check course announcements and Discord for any changes.

All classes meet Mondays 5:00 PM - 7:30 PM in Jacobs Hall Room 473, unless otherwise noted

Week 1: September 2

Labor Day - No Class

Week 2: September 8

Introduction to Visualization for Machine Learning

Lecture Topics:

• Course overview and logistics
• What is visualization for machine learning?
• Information visualization fundamentals
• The machine learning pipeline and where visualization fits

Lab Session:

• Development environment setup
• Introduction to D3.js
• Creating basic visualizations
• Git and project structure

Readings:

• Hohman et al. “Visual Analytics in Deep Learning: An Interrogative Survey” (2018)
• Munzner, “Visualization Analysis and Design”, Chapter 1

Assignment Released: Exercise 1 - Visualization Critique

Week 3: September 15

Course Introduction & Visualization Fundamentals

Lecture Topics:

• Course syllabus and logistics review
• What is Information Visualization?
• The Power of Visualization (Discovery, Storytelling, Exploration)
• Key concepts: Abstract data, Interaction, Amplifying cognition

Lab Session:

• Introduction to Observable and Vega-Lite
• Setting up accounts and development environment
• Creating first visualizations
• Understanding tidy data principles

Materials:

• Course Introduction Slides
• Vega-Lite Lab

Readings:

• Munzner, “Visualization Analysis and Design”, Chapter 1 (recommended)

Assignment: TBD

Week 4: September 22

Model Assessment and Performance Metrics

Lecture Topics:

• Classification metrics visualization
• Confusion matrices and ROC curves
• Regression model assessment
• Cross-validation visualization

Lab Session:

• Building performance dashboards
• Interactive metric exploration
• Comparative model visualization

Readings:

• Beauxis-Aussalet & Hardman, “Simplifying the Visualization of Confusion Matrix” (2014)

Due: Exercise 2
Assignment Released: Mini-Project 1

Week 5: September 29

White-box Model Visualization

Lecture Topics:

• Decision tree visualization
• Linear model interpretation
• Rule-based system visualization
• Feature importance displays

Lab Session:

• Implementing tree visualizations
• Interactive model exploration
• Feature contribution plots

Readings:

• Selected papers on interpretable ML

Project: Final project team formation

Week 6: October 6

Black-box Model Interpretation

Lecture Topics:

• LIME and SHAP explanations
• Partial dependence plots
• Feature interaction visualization
• Surrogate models

Lab Session:

• Implementing SHAP visualizations
• Building explanation interfaces
• Interactive what-if analysis

Readings:

• Ribeiro et al. “Why Should I Trust You?” (LIME paper)
• Lundberg & Lee “A Unified Approach to Interpreting Model Predictions” (SHAP)

Due: Mini-Project 1
Project: Final project proposals due

Week 7: October 13

Fall Break - No Class

Make-up Class: October 14 (Tuesday)

Deep Learning Visualization

Lecture Topics:

• Neural network architecture visualization
• Activation and gradient visualization
• CNN filter visualization
• Attention mechanism displays

Lab Session:

• TensorBoard integration
• Building network diagrams
• Interactive layer exploration

Readings:

• Zeiler & Fergus, “Visualizing and Understanding Convolutional Networks”
• Olah et al., “The Building Blocks of Interpretability”

Assignment Released: Mini-Project 2

Week 8: October 20

Clustering Visualization

Lecture Topics:

• Hierarchical clustering dendrograms
• K-means and cluster validation
• Cluster comparison techniques
• Uncertainty in clustering

Lab Session:

• Interactive clustering interfaces
• Cluster exploration tools
• Comparative analysis systems

Readings:

• Selected papers on cluster visualization

Project: Mid-term project presentations

Week 9: October 27

Dimensionality Reduction

Lecture Topics:

• PCA and linear projections
• t-SNE visualization
• UMAP and modern techniques
• Projection quality metrics

Lab Session:

• Implementing projection views
• Interactive parameter tuning
• Projection comparisons

Readings:

• van der Maaten & Hinton, “Visualizing Data using t-SNE”
• McInnes et al., “UMAP: Uniform Manifold Approximation and Projection”

Week 10: November 3

Topological Data Analysis

Lecture Topics:

• Persistence diagrams
• Mapper algorithm
• Reeb graphs
• Applications in ML

Lab Session:

• TDA tool integration
• Interactive topology exploration

Readings:

• Carlsson, “Topology and Data”

Due: Mini-Project 2
Assignment Released: Mini-Project 3

Week 11: November 10

NLP and Text Visualization

Lecture Topics:

• Word embeddings visualization
• Topic model visualization
• Attention in transformers
• Document similarity

Lab Session:

• Building text visualization systems
• Interactive embedding exploration

Readings:

• Selected papers on text visualization

Week 12: November 17

Time Series and Streaming Data

Lecture Topics:

• Temporal model performance
• Concept drift visualization
• Real-time monitoring
• Anomaly detection displays

Lab Session:

• Streaming visualization implementation
• Dashboard design patterns

Readings:

• Selected papers on temporal visualization

Week 13: November 24

Interpretable ML and Fairness

Lecture Topics:

• Fairness metrics visualization
• Bias detection interfaces
• Interpretability vs accuracy
• Ethical considerations

Lab Session:

• Fairness dashboard creation
• What-if tool exploration

Readings:

• Selected papers on ML fairness

Due: Mini-Project 3

Week 14: December 1

Project Presentations I

• Group project presentations (Part 1)
• Peer feedback sessions
• Q&A and discussions

Week 15: December 8

Project Presentations II

• Group project presentations (Part 2)
• Course wrap-up
• Future directions in VisML

Project: Final reports due December 11

Important Notes

1. Make-up Class: October 14 (Tuesday) replaces October 13 Fall Break
2. Thanksgiving Week: Check for updates regarding November 24 class
3. Office Hours: Will be posted on Discord
4. Slides: Available after each class on course website
5. Recordings: Posted for registered students who miss class

Assignment Summary