Amazon SageMaker Training Overview
This live, online or on-site Data Science with Amazon SageMaker training course teaches attendees how to solve a real-world use case with Machine Learning (ML) and produce actionable results using Amazon SageMaker. Participants are guided through the stages of a typical data science process for ML from analyzing and visualizing a dataset to preparing the data. Students also learn practical aspects of model building, training, tuning, and deployment with Amazon SageMaker.
Accelebrate is an AWS Training Partner (ATP) and this hands-on official AWS Classroom Training course is taught by an accredited Amazon Authorized Instructor (AAI).
Location and Pricing
Accelebrate offers instructor-led enterprise training for groups of 3 or more online or at your site. Most Accelebrate classes can be flexibly scheduled for your group, including delivery in half-day segments across a week or set of weeks. To receive a customized proposal and price quote for private corporate training on-site or online, please contact us.
In addition, some courses are available as live, instructor-led training from one of our partners.
Objectives
- Prepare a dataset for training
- Train and evaluate a Machine Learning model
- Automatically tune a Machine Learning model
- Prepare a Machine Learning model for production
- Think critically about Machine Learning model results
Prerequisites
- Familiarity with Python programming language
- Basic understanding of Machine Learning
Outline
Expand All | Collapse All
Introduction to Machine Learning (ML)
- Types of ML
- Job Roles in ML
- Steps in the ML pipeline
Introduction to Data Prep and SageMaker
- Training and test dataset defined
- Introduction to SageMaker
- SageMaker console
- Launching a Jupyter notebook
Problem Formulation and Dataset Preparation
- Business challenge: Customer churn
- Review customer churn dataset
Data Analysis and Visualization
- Loading and visualizing your dataset
- Relating features to target variables
- Relationships between attributes
- Cleaning the data
Training and Evaluating a Model
- Types of algorithms
- XGBoost and SageMaker
- Training the data
- Finishing the estimator definition
- Setting hyperparameters
- Deploying the model
- Hyperparameter tuning with SageMaker
- Evaluating model performance
Automatically Tune a Model
- Automatic hyperparameter tuning with SageMaker
- Tuning jobs
Deployment/Production Readiness
- Deploying a model to an endpoint
- A/B deployment for testing
- Auto Scaling
- Configure and test auto-scaling
- Check hyperparameter tuning job
- AWS Auto Scaling
- Practical Data Science with
- Amazon SageMaker
- AWS Classroom Training
- Set up AWS Auto Scaling
Relative Cost of Errors
- Cost of various error types
- Demo: Binary classification cutoff
Amazon SageMaker Architecture and Features
- Accessing Amazon SageMaker notebooks in a VPC
- Amazon SageMaker batch transforms
- Amazon SageMaker Ground Truth
- Amazon SageMaker Neo
Training Materials
All Amazon SageMaker training students will receive comprehensive courseware.
Software Requirements
A modern web browser and an Internet connection free of restrictive firewalls, so that the student can connect by SSH or Remote Desktop (RDP) into AWS virtual machines.
