Machine Learning on Google Cloud

Overview

What is machine learning, and what kinds of problems can it solve? How can you build, train, and deploy machine learning models at scale without writing a single line of code?

When should you use automated machine learning or custom training? This course teaches you how to build Vertex AI AutoML models without writing a single line of code; build BigQuery ML models knowing basic SQL; create Vertex AI custom training jobs you deploy using containers (with little knowledge of Docker); use Feature Store for data management and governance; use feature engineering for model improvement; determine the appropriate data preprocessing options for your use case; use Vertex Vizier hyperparameter tuning to incorporate the right mix of parameters that yields accurate, generalized models and knowledge of the theory to solve specific types of ML problems, write distributed ML models that scale in TensorFlow; and leverage best practices to implement machine learning on Google Cloud. > By enrolling in this specialization you agree to the Qwiklabs Terms of Service as set out in the FAQ and located at:

https:

//qwiklabs.com/terms_of_service

Syllabus

• Introduction to Machine Learning
Overview of machine learning concepts
Types of problems machine learning can solve
Introduction to Google Cloud's machine learning services
• Building Models with Vertex AI AutoML
Overview of Vertex AI AutoML
Steps for building models without coding
Use cases and applications
• BigQuery ML and SQL
Introduction to BigQuery ML
Writing SQL for machine learning
Building and deploying models using SQL
• Custom Training with Vertex AI
Introduction to Vertex AI custom training
Creating and deploying training jobs using containers
Basics of Docker for machine learning
• Feature Store for Data Management
Introduction to Google Cloud Feature Store
Data management and governance practices
Feature engineering techniques for model improvement
• Data Preprocessing Options
Assessing and choosing appropriate preprocessing strategies
Real-world preprocessing scenarios and solutions
• Hyperparameter Tuning with Vertex Vizier
Overview of Vertex Vizier
Importance of hyperparameter tuning
Methods to improve model accuracy and generalization
• Distributed Machine Learning in TensorFlow
Introduction to distributed training with TensorFlow
Writing scalable TensorFlow ML models
Best practices for distributed machine learning
• Best Practices for Implementing ML on Google Cloud
Best practices overview
Security, scalability, and efficiency considerations
Resources for continued learning and support
• Course Conclusion
Recap of key concepts and tools
Final project or case study application
Future learning paths in machine learning and Google Cloud
• Enrolling in Qwiklabs (Terms of Service)
Agreement to terms
Access to labs and practice exercises

Taught by

Google Cloud Training

Subjects

Programming