The final project should be technical, employing methods including, but not limited to, those covered in class (e.g., identify a real-world problem and apply relevant algorithms learned). Please keep your code and visualized results in Jupyter notebooks or well-organized code structure. Teams with multiple students may divide experiments across several notebooks. Each team is also required to present their project detailing the project’s background (motivation), methodology, and results.
Machine Learning at UVA (ML@UVA), the university’s leading machine learning club with 300+ members and faculty advisors. We collaborate with UVA departments, research labs, and industry partners to tackle real-world challenges through data-driven innovation.
This year, they are collaborating on joint projects with Logistics Management Institute (LMI) and Johns Hopkins APL. Since your course covers machine learning fundamentals and AI techniques, and we are pursuing projects in neural networks, computer vision, graph analysis, and anomaly detection
| Tool | Description |
|---|---|
| OpenAI GPT-4o / GPT-4o-mini | Free-tier LLM access via ChatGPT or API for text, image, and code. |
| Claude 3.5 Sonnet (Anthropic) | Strong at summarization and reasoning. |
| Google Gemini 1.5 | Integrates text + image + code tasks. |
| LangChain | Framework for building LLM workflows. |
| LlamaIndex | Simplifies data ingestion and RAG for custom knowledge. |
| Gradio | Quick web app demos for ML models. |
| GitHub Copilot / CodeWhisperer | AI coding partners for faster development. |