Machine Learning Fundamentals with Amazon SageMaker on AWS

Video description

5+ Hours of Video Instruction

Machine Learning Fundamentals with Amazon SageMaker on AWS LiveLessons teaches the fundamental concepts and taxonomy for machine learning and provides a high-level overview of the tools, languages, and libraries that Amazon SageMaker uses, including the AWS console, Jupyter Notebooks, languages, and interactive data analysis libraries.


Machine Learning Fundamentals with Amazon SageMaker on AWS LiveLessons teaches the fundamental concepts and taxonomy for machine learning. It provides specific scenarios, so the user can determine if ML would be beneficial. The course also provides a high-level overview of the tools, languages, and libraries that Amazon SageMaker uses, including the AWS console, Jupyter Notebooks, languages such as Python, and interactive data analysis libraries such as Pandas. This course will also discusses common algorithms and models used with ML and Amazon SageMaker, which will help determine the appropriate model to use in specific business scenarios.

Through this course the user will walk through Amazon SageMaker’s end-to-end workflow using practical and pragmatic business scenarios. You’ll see how you can benefit from the ability of a machine to make predictions on future data through hands-on labs and key concepts. AWS is continuing to make great strides to innovate their Artificial Intelligence and Machine Learning Platform. The concepts learned in this course will provide you with the foundation to build your own innovative systems on this dynamic platform.

Topics include:

Module 1: What is Amazon SageMaker?
Module 2: Fundamentals Machine Learning Concepts with Practical Applications
Module 3: Amazon SageMaker Supporting Tools and Technologies
Module 4: Data and Model Management with Amazon SageMaker
Module 5: Predictions and Deployment with Amazon SageMaker

About the Instructor

Asli Bilgin is an award-winning, cloud computing executive who has more than two decades of experience working for companies such as Dell, Microsoft, and Amazon. Her firm, Nokta Consulting, specializes in IT transformation and modernization leveraging disruptive technologies such as cloud computing, machine learning, and blockchain. At Amazon, Asli created, launched, and ran the global Software as a Service program. At Microsoft, she led the cloud and web strategy for 80 countries in the Middle East and Africa, based out of Dubai. Asli is a passionate advocate for the impact that technology can make on people’s lives. She was the architect behind the LEGO and Microsoft partnership effort for WomenBuild, a program to promote compute science as an art and science specifically for girls and women.

Skill Level

  • Beginner

Learn How To

  • Understand key machine learning concepts and taxonomy
  • Identify appropriate use cases and business scenarios than can benefit from Amazon SageMaker
  • Leverage the languages, libraries, and tools used in conjunction with Amazon SageMaker
  • Identify, prepare, and load data for analysis with Amazon SageMaker
  • Build and train datasets, train and fine tune models, create predictions and deploy these models to production using Amazon SageMaker
  • Use Amazon SageMaker with the AWS Console & SageMaker Dashboard
  • Couple conceptual knowledge with the hands-on experience to generate real time and batch predictions
  • Use common tools used in Machine Learning such as Jupyter Notebooks
  • Walk away with a preliminary understanding of the languages and libraries used with Machine Learning

Who Should Take This Course

  • Data scientist or developer who would like to build, train, and deploy machine learning models with speed and ease
  • Software programmers or data analysts who want to remain current on the latest AI/ML developments
  • Anyone wanting to learn the fundamentals of machine learning including concepts, taxonomy, workflow, and tools
  • Anyone wanting to accelerate your learning of Amazon SageMaker by learning principles combined with pragmatic experience

Course Requirements

  • An AWS Account, should you wish to follow along (AWS Free Tier can be used for 2 months.)
  • Ideally, have some experience with AWS, but not required
  • Ideally, you should have familiarity with software languages used with data analytics or software development preferred (for example, Python, R)

Lesson Descriptions

Module 1, “What is Amazon SageMaker?,” provides a history of the evolution of AI and ML. The benefits of Amazon SageMaker will be reviewed and sample use cases are provided. After you’re comfortable with the basics, you'll learn about how Amazon SageMaker works. We’ll talk about the lifecycle of ML processing and options for data sources. In the last lesson, we’ll do a walkthrough of the Amazon SageMaker console and discuss the various sub-services available within Amazon SageMaker. By the end of this module, you should be able to explain Amazon SageMaker to your friends and have some experience with the AWS Console.

Module 2, “Fundamentals Machine Learning Concepts with Practical Applications,” dives into the taxonomy and terms used in the machine-learning world. This module is all about information architecture, including features, observations, and ground truth. We’ll learn about what makes good data and how you can make intelligent choices with preparing your data for Amazon ML.

Module 3, “Amazon SageMaker Supporting Tools and Technologies.” After a quick refresher on key technologies used in conjunction with Amazon SageMaker, the remainder of this module is entirely composed of demos, which is designed to share the hands-on experience creating a new Amazon SageMaker data source, configuring that data source, and refining the schema. We’ll work directly with the S3 and the Amazon SageMaker console and experiment with features on managing your Amazon SageMaker data source. We will do this by leveraging the sample notebooks and algorithms provided by Amazon SageMaker.

Module 4, “Data and Model Management with Amazon SageMaker,” will show how to prepare and upload data to Amazon S3. Using a real-life example, we’ll spend two lessons on learning about algorithms so that we can build an appropriate model. After we have our model in place, we’ll cover tips on how you can assess performance and fine tune the model as necessary.

Module 5, “Predictions and Deployment with Amazon SageMaker,” talks about deployment and dives into predictions and determining future data. So far, we have provided you with the tools to construct quality datasets so that your SageMaker model performs well. Now, we will deploy that model in order to conduct predictions. This is a great way to build sales forecasts, as well as value a curated collection. It also provides some helpful cleanup tips so that you don’t incur unnecessary charges.

About Pearson Video Training

Pearson publishes expert-led video tutorials covering a wide selection of technology topics designed to teach you the skills you need to succeed. These professional and personal technology videos feature world-leading author instructors published by your trusted technology brands: Addison-Wesley, Cisco Press, Pearson IT Certification, Prentice Hall, Sams, and Que. Topics include: IT Certification, Network Security, Cisco Technology, Programming, Web Development, Mobile Development, and more. Learn more about Pearson Video training at

Table of contents

  1. Introduction
    1. Machine Learning Fundamentals with Amazon SageMaker on AWS: Introduction
  2. Module 1: What is Amazon SageMaker?
    1. Module introduction
  3. Lesson 1: Amazon Artificial Intelligence and Machine Learning Overview
    1. Learning objectives
    2. 1.1 Evolution of Artificial Intelligence (AI) and Machine Learning (ML)
    3. 1.2 What is ML?
    4. 1.3 AWS ML AI: Platform Services
    5. 1.4 AWS ML AI: Application Services
    6. 1.5 AWS ML AI: Foundational Services
    7. 1.6 Sample AI/ML Case Studies with AWS
  4. Lesson 2: How Does Amazon SageMaker Work?
    1. Learning objectives
    2. 2.1 What is Amazon SageMaker?
    3. 2.2 Who Should use Amazon SageMaker?
    4. 2.3 What are the Benefits of Amazon SageMaker?
    5. 2.4 High Level Overview
    6. 2.5 Options for Data Sources
    7. 2.6 Supervised Machine Learning
    8. 2.7 Unsupervised Machine Learning
    9. 2.8 Life Cycle of ML Processing
  5. Lesson 3: Which Use Cases Can Amazon SageMaker Solve?
    1. Learning objectives
    2. 3.1 Personalization
    3. 3.2 Search
    4. 3.3 Marketing
    5. 3.4 Finance
    6. 3.5 Personal Productivity
    7. 3.6 Product Management
  6. Lesson 4: High Level Overview of the Amazon SageMaker Components
    1. Learning objectives
    2. 4.1 Components of Amazon SageMaker
    3. 4.2 Demo: AWS SageMaker Console
    4. 4.3 Amazon SageMaker Notebooks Service
    5. 4.4 Amazon SageMaker Training Service
    6. 4.5 Amazon SageMaker Hosting Service
    7. 4.6 Pricing
  7. Module 2: Fundamental Machine Learning Concepts with Practical Applications
    1. Module introduction
  8. Lesson 5: Machine Learning Concepts and Taxonomy
    1. Learning objectives
    2. 5.1 What is Input Data?
    3. 5.2 What are Features?
    4. 5.3 What is a Target?
    5. 5.4 What are Observations?
    6. 5.5 What is Labeled Data?
    7. 5.6 What is Unlabeled Data?
    8. 5.7 What is Ground Truth?
    9. 5.8 What are Hyperparameters?
    10. 5.9 What are Predictions or Inferences
  9. Lesson 6: Selecting the Appropriate Data
    1. Learning objectives
    2. 6.1 What is the Best Kind of Data?
    3. 6.2 Academic and Commercial Sources for Data
    4. 6.3 Sample Business Problem for This Course
  10. Lesson 7: Practical Applications for Machine Learning
    1. Learning objectives
    2. 7.1 How to Frame a Suitable Problem
    3. 7.2 Scenarios
    4. 7.3 Curator Project Sample Business Problem
    5. 7.4 Best Practices for Selecting a Business Problem
  11. Module 3: Amazon SageMaker Supporting Tools and Technologies
    1. Module introduction
  12. Lesson 8: Refresher on Technologies Leveraged by Amazon SageMaker
    1. Learning objectives
    2. 8.1 Amazon S3
    3. 8.2 EC2 Instances
    4. 8.3 Identity Access Management (IAM)
    5. 8.4 Taxonomy
    6. 8.5 Key Packages and Libraries
    7. 8.6 Package Management and SDKs
  13. Lesson 9: Interactive Lab: Review the SageMaker Console
    1. Learning objectives
    2. 9.1 Login to AWS Console
    3. 9.2 Amazon SageMaker Dashboard Walkthrough
  14. Lesson 10: Interactive Lab: Working with Jupyter Notebooks
    1. Learning objectives
    2. 10.1 Components of Jupyter Notebooks
    3. 10.2 Jupyter Notebooks and Amazon SageMaker
    4. 10.3 Tips for Code Execution
    5. 10.4 Demo: Create a Notebook Instance
  15. Lesson 11: Interactive Lab: Example SageMaker Notebooks
    1. Learning objectives
    2. 11.1 High Level Overview
    3. 11.2 Common Algorithms with Amazon SageMaker Samples
    4. 11.3 How to Bring Your Own Algorithm
    5. 11.4 Interactive Lab: Review Amazon SageMaker Pre-built Notebook Types
    6. 11.5 Interactive Lab: Walkthrough of a Pre-built Sample Jupyter Notebook
  16. Module 4 Data and Model Management with Amazon SageMaker
    1. Module introduction
  17. Lesson 12: Interactive Lab: Working with Jupyter Notebooks
    1. Learning objectives
    2. 12.1 Best Practices for Scrubbing Data
    3. 12.2 Best Practices for Handling Missing Values
    4. 12.3 Demo: Source Data from SQL Server
    5. 12.4 Demo: Feature Selection
    6. 12.5 Interactive Lab: Create an S3 Bucket and Folder
    7. 12.6 Interactive Lab: Upload Data through AWS Console
    8. 12.7 Interactive Lab: Visualization Demo
  18. Lesson 13: A Closer Look at Algorithms
    1. Learning objectives
    2. 13.1 How to Approach Learning ML Algorithms
    3. 13.2 Sample Popular Algorithms
    4. 13.3 Choosing an Algorithm
    5. 13.4 Interactive Lab: Demo of a Popular Algorithm
  19. Lesson 14: Algorithm Selection
    1. Learning objectives
    2. 14.1 Choose the Appropriate Algorithm
    3. 14.2 Create Features and Labels
    4. 14.3 Split Data - Training, Validation, Test
  20. Lesson 15: Model Training
    1. Learning objectives
    2. 15.1 Overview of Model Training with Amazon SageMaker
    3. 15.2 Model Training Workflow
    4. 15.3 Model Training and Evaluation Tips
    5. 15.4 Running High Compute Taining Jobs with EC2 Instances
  21. Lesson 16: Assess Model Performance
    1. Learning objectives
    2. 16.1 How to Evaluate Model Performance
    3. 16.2 Sample Metrics for Assessing Accuracy Using Common Models
    4. 16.3 Subjective Analysis
    5. 16.4 Objective Analysis Using Tools
    6. 16.5 Common Causes of Poor Performance
    7. 16.6 How to Refine Your Model
  22. Module 5 Predictions and Deployment with Amazon SageMaker
    1. Module introduction
  23. Lesson 17: Deploy Model
    1. Learning objectives
    2. 17.1 Overview Amazon SageMaker Hosting Services
    3. 17.2 How to Create an Endpoint with Elastic Inference
    4. 17.3 Deploy Model
    5. 17.4 Demo: Curator
  24. Lesson 18: Predictions or Inferences
    1. Learning objectives
    2. 18.1 How do Predictions Work?
    3. 18.2 What are the Types of Predictions?
    4. 18.3 Generate Real Time Predictions
    5. 18.4 Batch Predictions
    6. 18.5 Cleanup
  25. Lesson 19: Call to Action Conclusion
    1. Learning objectives
    2. 19.1 Final Review
    3. 19.2 Next Steps
    4. 19.3 References
  26. Summary
    1. Machine Learning Fundamentals with Amazon SageMaker on AWS: Summary

Product information

  • Title: Machine Learning Fundamentals with Amazon SageMaker on AWS
  • Author(s): Asli Bilgin
  • Release date: November 2019
  • Publisher(s): Pearson
  • ISBN: 0135945135