.png?width=22&height=21&name=Artificial%20Intelligence%20(AI).png){kind=small}
/AI%20(6)-1-1.png?width=50&height=50&name=AI%20(6)-1-1.png)
Building machine learning models is only the beginning. Operationalising them at scale requires robust pipelines, orchestration, and ongoing monitoring. This intermediate-level course equips participants with the practical skills to build, deploy, and maintain machine learning solutions using Amazon Web Services (AWS). Through hands-on labs and real-world scenarios, they will use tools such as Amazon SageMaker, Amazon EMR, and Model Monitor to develop secure and scalable ML systems. The course covers MLOps workflows, model tuning, data processing, and drift management in production environments.
Learning Outcomes
Understand machine learning principles and their application in AWS
Process and engineer data for ML tasks using AWS tools
Select and apply appropriate ML algorithms for given problem types
Implement scalable training and deployment pipelines with Amazon SageMaker
Monitor deployed models and respond to data drift or performance issues
Automate ML workflows using MLOps tools and practices
Key Topics
Amazon SageMaker and SageMaker Studio
Data preparation with Amazon S3, Glue, and EMR
Model training, tuning, and deployment
MLOps automation with SageMaker Pipelines
Model monitoring using SageMaker Model Monitor
Securing and scaling ML systems on AWS
Exam Details
This course is designed to build participants’ understanding of key concepts and domains covered in the AWS Machine Learning Engineer – Associate certification.
| Exam Format | Multiple choice or multiple response |
| Delivery | Pearson VUE testing centre |
| Duration | 130 minutes |
| Number of Questions | 65 |
| Open Book | No |
| Passing Score | 720 |
To maximise success, participants are strongly encouraged to complement the course with additional self-study, revision of course materials, and dedicated practice before attempting the exam.
Day 1
Module 0: Course Introduction
Module 1: Introduction to Machine Learning (ML) on AWS Topic A: Introduction to ML
Topic B: Amazon SageMaker AI Topic C: Responsible ML
Module 2: Analysing Machine Learning (ML) Challenges Topic A: Evaluating ML business challenges
Topic B: ML training approaches Topic C: ML training algorithms
Module 3: Data Processing for Machine Learning (ML) Topic A: Data preparation and types
Topic B: Exploratory data analysis
Topic C: AWS storage options and choosing storage Module 4: Data Transformation and Feature Engineering
Topic A: Handling incorrect, duplicated, and missing data Topic B: Feature engineering concepts
Topic C: Feature selection techniques Topic D: AWS data transformation services
Lab 1: Analyse and Prepare Data with Amazon SageMaker Data Wrangler and Amazon EMR
Lab 2: Data Processing Using SageMaker Processing and the SageMaker Python SDK
Day 2
Module 5: Choosing a Modelling Approach
Topic A: Amazon SageMaker AI built-in algorithms Topic B: Amazon SageMaker Autopilot
Topic C: Selecting built-in training algorithms Topic D: Model selection considerations Topic E: ML cost considerations
Module 6: Training Machine Learning (ML) Models Topic A: Model training concepts
Topic B: Training models in Amazon SageMaker AI Lab 3: Training a model with Amazon SageMaker AI
Module 7: Evaluating and Tuning Machine Learning (ML) models Topic A: Evaluating model performance
Topic B: Techniques to reduce training time Topic C: Hyperparameter tuning techniques
Lab 4: Model Tuning and Hyperparameter Optimisation with Amazon SageMaker AI Module 8: Model Deployment Strategies
Topic A: Deployment considerations and target options Topic B: Deployment strategies
Topic C: Choosing a model inference strategy
Topic D: Container and instance types for inference Lab 5: Shifting Traffic
Day 3
Module 9: Securing AWS Machine Learning (ML) Resources
Topic A: Access control
Topic B: Network access controls for ML resources Topic C: Security considerations for CI/CD pipelines
Module 10: Machine Learning Operations (MLOps) and Automated Deployment
Topic A: Introduction to MLOps
Topic B: Automating testing in CI/CD pipelines Topic C: Continuous delivery services
Lab 6: Using Amazon SageMaker Pipelines and the Amazon SageMaker Model Registry with Amazon SageMaker Studio
Module 11: Monitoring Model Performance and Data Quality Topic A: Detecting drift in ML models
Topic B: SageMaker Model Monitor
Topic C: Monitoring for data quality and model quality Topic D: Automated remediation and troubleshooting Lab 7: Monitoring a Model for Data Drift
Module 12: Course Wrap-up
