Course
Digicomp Code AIMLGC
Introduction to AI and Machine Learning on Google Cloud («AIMLGC»)
This course introduces the AI and machine learning (ML) offerings on Google Cloud that build both predictive and generative AI projects.
Duration
1 day
Price
850.–
Course documents
Official Google Cloud courseware
Course facts
- Recognizing the data-to-AI technologies and tools provided by Google Cloud
- Building generative AI projects by using Gemini multimodal, efficient prompts, and model tuning
- Exploring various options for developing an AI project on Google Cloud
- Creating an ML model from end-to-end by using Vertex AI
Explore the technologies, products, and tools available throughout the data-to-AI life cycle, encompassing AI foundations, development, and solutions. This course aims to help data scientists, AI developers, and ML engineers enhance their skills and knowledge through engaging learning experiences and practical hands-on exercises.
1 AI Foundations
- Why AI?
- AI/ML framework on Google Cloud
- Google Cloud infrastructure
- Data and AI products
- ML model categories
- BigQuery ML
- Lab introduction: BigQuery ML
- Recognize the AI/ML framework on Google Cloud
- Identify the major components of Google Cloud infrastructure
- Define the data and ML products on Google Cloud and how they support the data-to-AI lifecycle
- Build an ML model with BigQueryML to bring data to AI
- Lab: Predicting Visitor Purchases with BigQuery ML
2 AI Development Options
- Pre-trained APIs
- Vertex AI
- AutoML
- Custom training
- Lab introduction: Natural Language API
- Define different options to build an ML model on Google Cloud
- Recognize the primary features and applicable situations of pre-trained APIs, AutoML, and custom training
- Use the Natural Language API to analyze text
- Lab: Entity and Sentiment Analysis with Natural Language API
3 AI Development Workflow
- ML workflow
- Data preparation
- Model development
- Model serving
- MLOps and workflow automation
- Lab introduction: AutoML
- How a machine learns
- 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 on Vertex AI
- Lab: Vertex AI: Predicting Loan Risk with AutoML
4 Generative AI
- Generative AI and workflow
- Gemini multimodal
- Prompt design
- Model tuning
- Model Garden
- AI solutions
- Lab introduction: Vertex AI Studio
- Define generative AI and foundation models
- Use Gemini multimodal with Vertex AI Studio
- Design efficient prompt and tune models with different methods
- Recognize the AI solutions and the embedded Gen AI features
- Lab: Getting Started with Vertex AI Studio
Professional AI developers, data scientists, and ML engineers who want to build predictive and generative AI projects on Google Cloud
Having one or more of the following:
- Basic knowledge of machine learning concepts
- Prior experience with programming languages such as SQL and Python
Products
- Vertex AI
- Gemini multimodal
- AutoML
- BigQuery ML
- Vertex AI Pipelines
- TensorFlow
- Model Garden
- Vertex AI Studio
- Natural Language API
- Contact Center AI (CCAI)