Course Description
This course introduces the artificial intelligence (AI) and machine learning (ML) offerings on Google Cloud that support the data-to-AI lifecycle through AI foundations, AI development, and AI solutions. It explores the technologies, products, and tools available to build an ML model, an ML pipeline, and a generative AI project based on the different goals of users, including data scientists, AI developers, and ML engineers.
Objectives
- Recognize the data-to-AI technologies and tools offered by Google Cloud
- Use generative AI capabilities in applications
- Choose between different options to develop an AI project on Google Cloud
- Build ML models end-to-end by using Vertex AI
Prerequisites
Having one or more of the following:
- Basic knowledge of machine learning concepts
- Prior experience with programming languages such as SQL and Python
Audience
Professional AI developers, data scientists, and ML engineers who want to build ML models, develop AI or ML applications or solutions and build end-to-end ML pipelines on Google Cloud
Course Outline
Module 1: Course Introduction
- Define the course goal
- Recognize the course objectives
Module 2: AI Foundations
- Why Google?
- AI/ML framework on Google Cloud
- Google Cloud infrastructure
- Data and AI products
- ML model categories
- BigQuery ML
- Lab introduction: BigQuery ML
Module 3: AI Development Options
- AI development options
- Pre-trained APIs
- Vertex AI
- AutoML
- Custom training
- Lab introduction: Natural Language API
Module 4: AI Development Workflow
- How a machine learns
- ML workflow
- Data preparation
- Model development
- Model serving
- MLOps and workflow automation
- Lab introduction: AutoML
Module 5: Generative AI
- Generative AI and LLM
- Generative AI use case: Duet AI
- Model Garden
- Generative AI Studio
- AI solutions
- Lab introduction: Generative AI Studio