Intro to Google Cloud Platform (GCP) for Machine Learning and AI

This lesson teaches core workflows for building, training, and tuning ML/AI models using Google Cloud's Vertex AI platform. Participants learn to set up data storage, configure Vertex AI Workbench notebooks as lightweight controllers, launch training and hyperparameter tuning jobs, and optimize resource costs effectively within GCP. The workshop also includes a section on building retrieval-augmented generation (RAG) pipelines using Gemini models.

Prerequisites

• Intro to Machine Learning
• Basic Python Programming

Episodes

1. Overview of Google Cloud for Machine Learning
2. Data Storage: Setting up GCS
3. Notebooks as Controllers
4. Accessing and Managing Data in GCS
5. Using GitHub PAT in Vertex AI Notebooks
6. Training Models in Vertex AI: XGBoost (CPU)
7. Training Models in Vertex AI: PyTorch (GPU)
8. Hyperparameter Tuning in Vertex AI
9. Resource Management & Cleanup
10. Retrieval-Augmented Generation (RAG)

Setup

See the Setup page for instructions on preparing for this workshop.

About

This lesson uses The Carpentries Workbench and is part of The Carpentries Incubator.

Contact

For questions or issues, contact endemann@wisc.edu or open an issue on this repository.