Machine Learning Basics with AWS SageMaker Training Course
Course Overview
Analysts and developers new to AWS learn to build, train and deploy machine learning models in Amazon SageMaker. Day one covers the SageMaker interface, data preparation and feature engineering, and a first regression model using a built-in algorithm. Day two moves to distributed training and hyperparameter tuning, custom scripts in Jupyter Notebooks and automated SageMaker Pipelines. Day three deploys models to real-time endpoints and batch inference, then watches them with SageMaker Model Monitor and handles version updates. The course closes with a group case where attendees build and present a full SageMaker solution to a business problem.
Format of Training
- Live demos in the AWS SageMaker console and Jupyter Notebooks
- Labs that run from a first regression model to a monitored endpoint
- Sample datasets used for feature engineering and tuning work
- Case-based group work on a complete SageMaker build
Course Objectives
- Describe the main features and services in Amazon SageMaker.
- Prepare and transform data for ML with AWS tools.
- Train SageMaker models and measure how well they perform.
- Deploy trained models to AWS endpoints that scale.
- Work with both SageMaker built-in algorithms and your own training scripts.
- Track deployed models and tune them for better results.
- Run complete ML workflows in SageMaker on practical problems.
Prerequisites
- Familiarity with basic ML concepts
- Python skills help but are not required
- An interest in machine learning on the cloud
- Openness to hands-on lab work
Course Outline
Day 1
Session 1: Introduction to AWS SageMaker and Machine Learning Basics
- What AWS SageMaker includes and how its services connect
- Core ML ideas and where they are applied
- Hands-on lab: setting up SageMaker and learning its interface
Session 2: Preparing Data for Machine Learning in SageMaker
- Loading and preprocessing data with AWS tools
- Transforming data and engineering features in SageMaker
- Hands-on lab: getting a dataset ready for ML
Session 3: Building Your First Machine Learning Model
- Fitting a simple regression model with a SageMaker built-in algorithm
- Scoring the model with basic metrics
- Hands-on lab: creating a regression model and testing it
Day 2
Session 1: Training and Tuning Machine Learning Models
- SageMaker training options: distributed training and hyperparameter tuning
- Good habits for getting better model results
- Hands-on lab: tuning an ML model inside SageMaker
Session 2: Working with SageMaker Notebooks
- Developing custom models in Jupyter Notebooks
- Writing training scripts and running them in SageMaker
- Hands-on lab: coding a custom ML workflow in a notebook
Session 3: Introduction to SageMaker Pipelines
- Automating ML work with SageMaker Pipelines
- Designing pipelines that can be reused across ML projects
- Hands-on lab: building a SageMaker Pipeline and running it
Day 3
Session 1: Deploying Machine Learning Models in AWS SageMaker
- Putting trained models behind real-time endpoints
- Batch inference and feeding predictions into applications
- Hands-on lab: launching an endpoint and checking its predictions
Session 2: Monitoring and Managing Deployed Models
- Watching model performance with SageMaker Model Monitor
- Handling model versions and rolling out updates
- Hands-on lab: monitoring a live model in AWS
Session 3: Case Study: Real-World ML Solution with SageMaker
- Tackling a business problem with SageMaker tools
- Group activity: building an end-to-end solution and presenting it
Book This Course
Customise This Course for Your Team
If your organization already has an AWS account, the labs can run there on data your team knows. Teams focused on production can spend more of Day 3 on endpoints, batch inference and Model Monitor. Let us know which AWS services you use today.
Need help with the right course to choose?
Explore more opportunities
- Duration: 1 Day
- 4.5 Ratings
Introduction to Machine Learning and AI Training Course
- Duration: 2 Days
- 4.5 Ratings
Machine Learning with Python for Beginners Training Course
- Duration: 3 Days
- 4.5 Ratings
Machine Learning Fundamentals with TensorFlow Training Course
- Duration: 2 Days
- 4.5 Ratings
Data Preprocessing and Feature Engineering for Machine Learning Training Course
- Duration: 3 Days
- 4.5 Ratings
Supervised and Unsupervised Learning Essentials Training Course
- Duration: 3 Days
- 4.5 Ratings
Introduction to Machine Learning with R Training Course