Course
Digicomp Code GCPML
Machine Learning on Google Cloud («GCPML»)
An introduction to 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.
Duration
5 days
Price
4'250.–
Course documents
Official Google Cloud courseware
Course facts
- Describing the technologies, products, and tools to build an ML model, an ML pipeline, and a Generative AI project
- Understanding when to use AutoML and BigQuery ML
- Creating Vertex AI-managed datasets
- Adding features to the Vertex AI Feature Store
- Describing Analytics Hub, Dataplex, and Data Catalog
- Describing how to improve model performance
- Creating Vertex AI Workbench user-managed notebook, building a custom training job, and deploying it by using a Docker container
- Describing batch and online predictions and model monitoring
- Describing how to improve data quality and explore your data
- Building and training supervised learning models
- Optimizing and evaluating models by using loss functions and performance metrics
- Creating repeatable and scalable train, eval, and test datasets
- Implementing ML models by using TensorFlow or Keras
- Understanding the benefits of using feature engineering
- Explaining Vertex AI Model Monitoring and Vertex AI Pipelines
This course explores the technologies, products, and tools available to build an ML model, an ML pipeline, and a generative AI project. You learn how to build AutoML models without writing a single line of code; build BigQuery ML models using SQL, and build Vertex AI custom training jobs by using Keras and TensorFlow. You also explore data preprocessing techniques and feature engineering.
1 Introduction to AI and Machine Learning on Google Cloud
- 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
- 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
- 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
- Define generative AI and large language models
- Use generative AI capabilities in AI development
- Recognize the AI solutions and the embedded generative AI features
2 Launching into Machine Learning
- Describe how to improve data quality
- Perform exploratory data analysis
- Build and train supervised learning models
- Describe AutoML and how to build, train, and deploy an ML model without writing a single line of code
- Describe BigQuery ML and its benefits
- Optimize and evaluate models by using loss functions and performance metrics
- Mitigate common problems that arise in machine learning
- Create repeatable and scalable training, evaluation, and test datasets
3 TensorFlow on Google Cloud
- Create TensorFlow and Keras machine learning models
- Describe the TensorFlow main components
- Use the tf.data library to manipulate data and large datasets
- Build a ML model that uses tf.keras preprocessing layers
- Use the Keras Sequential and Functional APIs for simple and advanced model creation
- Train, deploy, and productionalize ML models at scale with the Vertex AI Training Service
4 Feature Engineering
- Describe Vertex AI Feature Store
- Compare the key required aspects of a good feature
- Use tf.keras.preprocessing utilities for working with image data, text data, and sequence data
- Perform feature engineering by using BigQuery ML, Keras, and TensorFlow
5 Machine Learning in the Enterprise
- Understand the tools required for data management and governance
- Describe the best approach for data preprocessing: From providing an overview of Dataflow and Dataprep to using SQL for preprocessing tasks
- Explain how AutoML, BigQuery ML, and custom training differ and when to use a particular framework
- Describe hyperparameter tuning by using Vertex AI Vizier to improve model performance
- Explain prediction and model monitoring and how Vertex AI can be used to manage ML models
- Describe the benefits of Vertex AI Pipelines
- Describe best practices for model deployment and serving, model monitoring, Vertex AI Pipelines, and artifact organization
- Aspiring machine learning data analysts, data scientists, and data engineers
- Learners who want exposure to ML and use Vertex AI, AutoML, BigQuery ML, Vertex AI Feature Store, Vertex AI Workbench, Dataflow, Vertex AI Vizier for hyperparameter tuning, and TensorFlow/Keras
- Some familiarity with basic machine learning concepts
- Basic proficiency with a scripting language, preferably Python
Products
- Vertex AI
- AutoML
- BigQuery ML
- Vertex AI Pipelines
- TensorFlow
- Model Garden
- Generative AI Studio
- Large language model (LLM) APIs
- Natural Language API
- Vertex AI Workbench
- Vertex AI Feature Store
- Vizier
- Dataplex
- Analytics Hub
- Data Catalog
- TensorFlow
- Vertex AI TensorBoard
- Dataflow
- Dataprep
- Vertex AI Pipelines