Course Overview
This course introduces Google Cloud's AI and machine learning (ML) capabilities, with a focus on developing both generative and predictive AIprojects. It explores the various technologies, products, and tools available throughout the data-to-AI lifecycle, empowering data scientists, AI developers, and ML engineers to enhance their expertise through interactive exercises.
Course Content
- Introduction
- AI foundations
- Generative AI
- AI development options
- AI development worklow
- Summary
Who should attend
Data scientists, AI developers, ML engineers
Certifications
This course is part of the following Certifications:
Prerequisites
- Basic knowledge of machine learning concepts
- Prior experience with programming languages such as SQL and Python
Course Objectives
- Recognize the data-to-AI technologies and tools provided by Google Cloud.
- Build generative AI projects by using Gemini multimodal, efficient prompts, and AI agent builders.
- Choose between different Google Cloud product options to develop an AI project.
- Create an ML model from end-to-end by using Vertex AI.
Follow On Courses
Outline: Introduction to AI and Machine Learning on Google Cloud (AIMLGC)
Introduction
This lesson guides learners through the course structure, which is built upon a three-layer AI framework: AI infrastructure, development, and solutions. It outlines the learning objectives and introduces learners to Google's comprehensive suite of full-stack AI development tools.
- Define the course objectives.
- Recognize the course structure.
AI foundations
This module begins with a use case demonstrating the AI capabilities. It then focuses on the AI infrastructure like compute and storage. It also explains the primary data and AI development products on Google Cloud. Finally, it demonstrates how to use BigQuery ML to build an ML model, which helps transition from data to AI.
- Recognize the AI/ML framework on Google Cloud.
- Identify the major components of AI infrastructure.
- Define the data and ML products on Google Cloud and how they support the data-to-AI lifecycle.
- Build an ML model with BigQuery ML to bring data to AI.
Generative AI
This module introduces generative AI (gen AI), the latest AI advancement, and the Google Cloud toolkits for developing gen AI projects. It starts by examining the foundation models. It then investigates the prompt-to-production lifecycle with VertexAI Studio, including prompt engineering, app deployment, and model tuning.Additionally, this module explores AI agents and Google’s full stack of AI agent development tools.
- Define generative AI and foundation models.
- Recognize the prompt-to-production lifecycle and its associated tools.
- Define AI agents and their core components.
- Identify Google Cloud tools and technologies for building AI agents.
AI development options
This module explores the various options for developing an AI project on GoogleCloud, from ready-made solutions like pre-trained APIs, to no-code and low-code solutions like AutoML, and code-based solutions like custom training. It compares the advantages and disadvantages of each option to help decide the right development tools.
- Define different options to build an ML model with Vertex AI on Google Cloud.
- Identify the features and use cases of pre-trained APIs, AutoML, and custom training.
- Use the Natural Language API to analyze text.
AI development worklow
This module walks through the ML workflow from data preparation, to model development, and to model serving on Vertex AI. It also illustrates how to convert the workflow into an automated pipeline using Vertex AI Pipelines.
- Define the workflow of building an ML model.
- Describe MLOps and workflow automation on Google Cloud.
- Build an ML model from end to end by using AutoML with Vertex AI.
Summary
This lesson summarizes the course by addressing the most important concepts, tools, technologies, and products for each module.
- Recognize the primary concepts, tools, technologies, and products learned in the course.