Table of contents
Introduction
AWS Certified Machine Learning Engineer - Associate: Introduction
Module 1: Data Preparation for Machine Learning
Module Introduction
Lesson 1: Data Ingestion and Storage Basics
Learning objectives
1.1 Course

Overview

1.2

Overview

of Common Data Formats
1.3 Ingesting Data with Amazon S3 and SageMaker Data Wrangler
1.4 Data Ingestion Demonstration
1.5 Data Storage Optimization and Transfer in AWS
Lesson 2: Data Transformation and Feature Engineering with SageMaker
Learning objectives
2.1 Data Cleaning and Preprocessing with SageMaker Data Wrangler
2.2 Data Preprocessing Demonstration
2.3 Feature Scaling and Encoding Techniques
2.4 Handling Missing Values and Outliers
Lesson 3: Preparing Data for Modeling
Learning objectives
3.1 Validating Data Quality with AWS Tools
3.2 Configuring Data for SageMaker Training Jobs
3.3 Managing SageMaker Feature Store
3.4 SageMaker Feature Store Demonstration
Module 2: ML Model Development
Module Introduction
Lesson 4: Choosing and Training Models in SageMaker
Learning objectives
4.1

Overview

of SageMaker's Built-in Algorithms and JumpStart Models
4.2 SageMaker Algorithms Demonstration
4.3 Setting Up and Running SageMaker Training Jobs
4.4 SageMaker Training Demonstration
4.5 Hyperparameter Tuning with SageMaker Automatic Model Tuning
4.6 Hyperparameter Tuning Demonstration
4.7 Preventing Overfitting and Underfitting
4.8 Model Over/Underfitting Demonstration
Lesson 5: Model Evaluation and Bias Detection
Learning objectives
5.1 Model Evaluation Metrics: Accuracy, Precision, and Recall
5.2 Using SageMaker Clarify for Bias Detection and Interpretability
5.3 Comparing Model Performance Using A/B Testing
5.4 Model A/B Testing Demonstration
5.5 Managing Model Versions with SageMaker Model Registry
5.6 Model Registry Demonstration
Module 3: Deployment and Orchestration of ML Workflows
Module Introduction
Lesson 6: Deploying Models with SageMaker
Learning objectives
6.1 Real-Time Inference with SageMaker Endpoints
6.2 Real-Time Inference Demonstration
6.3 Batch Inference and Asynchronous Inference
6.4 Batch and Asynchronous Inference Demonstration
6.5 Using SageMaker Neo for Edge Deployment
6.6 SageMaker Edge Deployment Demonstration
Lesson 7: Automating ML Workflows with SageMaker Pipelines
Learning objectives
7.1 Building and Automating ML Pipelines in SageMaker
7.2 SageMaker Pipeline Demonstration
7.3 Integrating Data Processing and Training Steps
7.4 Training and Data Processing in SageMaker Pipelines Demonstration
7.5 Triggering Pipelines with EventBridge for Retraining
7.6 Triggering SageMaker Pipelines via EventBridge Demonstration
Module 4: ML Solution Monitoring, Maintenance, and Security
Module Introduction
Lesson 8: Monitoring and Optimizing ML Solutions
Learning objectives
8.1 Using SageMaker Model Monitor for Data Drift and Quality
8.2 SageMaker Model Monitor Demonstration
8.3 Setting Up Alerts and CloudWatch Dashboards
8.4 Cost Optimization with Auto-scaling and SageMaker Savings Plans
8.5 SageMaker Auto-scaling Demonstration
Lesson 9: Securing ML Models and Data in SageMaker
Learning objectives
9.1 IAM Roles and Permissions for SageMaker
9.2 IAM Demonstration
9.3 VPC Configurations for Secure Endpoint Deployment
9.4 VPC Demonstration
Module 5: Exam Preparation and Strategy
Module Introduction
Lesson 10: Exam Strategies and Practice
Learning objectives
10.1 Key Focus Areas for the AWS ML Engineer Associate Exam
10.2 Exam Question Types and Tips for Multiple-Choice Questions
10.3 Time Management and Final Exam Day Tips
Summary
AWS Certified Machine Learning Engineer - Associate: Summary

https://www.oreilly.com/library/view/aws-certified-machine/9780135449288/