O'Reilly logo

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

Amazon Machine Learning

Video Description

Sneak Peek

The Sneak Peek program provides early access to Pearson video products and is exclusively available to Safari subscribers. Content for titles in this program is made available throughout the development cycle, so products may not be complete, edited, or finalized, including video post-production editing.

More Than 3 Hours of Video Instruction


Amazon Machine Learning LiveLessons is designed to provide a solid foundational understanding of the data preparation and evaluation that’s necessary to run predictive analysis with Machine Learning models. The course covers the concepts necessary to understand Amazon Machine Learning and teaches the user how to leverage the benefits of predictive analysis. Usage scenarios are provided to inspire viewers to create their own value-added services on top of Amazon Machine Learning.

Amazon Machine Learning LiveLessons contains more than 20 independent video lessons totaling more than 3 hours of instruction with demos, interactive labs, and detailed slide explanations. Hands-on labs with Amazon Machine Learning are included to provide necessary context and experience to create pragmatic applications. Viewers will walk away with a solid understanding of how Amazon Machine Learning is structured and how to apply it in their own scenarios.

Asli Bilgin’s knowledge comes from her unique experience working at Amazon and as a Machine Learning consultant for her business, Nokta Consulting. She uses her professional skills for her personal vintage jewelry business, oyacharm. She is an award-winning cloud computing executive who has more than two decades of experience working for companies such as Dell, Microsoft, and Amazon. She specializes in IT transformation and modernization leveraging disruptive technologies. At Amazon, Asli created, launched, and ran the global Software as a Service program and ran the Financial Services IT Transformation practice for AWS Professional Services. At Microsoft, she led the cloud and web strategy for 80 countries in the Middle East and Africa, based out of Dubai. In her early career, Asli served as a software developer, technical manager, and architect for large and complex enterprise projects.

Topics include
Module 1: Amazon Machine Learning Basics
Module 2: Amazon Machine Learning Data Architecture
Module 3: Data and Schema Configuration
Module 4: Machine Learning Visualization and Modeling
Module 5: Predictions with Amazon Machine Learning

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


Learn How To

  • Understand the concepts, taxonomy, and principles behind Machine Learning
  • Get started with the core Amazon Machine Learning service
  • Solve for personalization, search, marketing, finance, productivity, and management efficiency using AML
  • Configure a schema, and set up a data source using “small data” in S3
  • Use data insights and visualization tools
  • Leverage Features, Targets, Observations, Labeled Data, Unlabeled Data, and Ground Truth to prepare historical data for predictive analysis
  • Prepare data for use in a regression model and a multi-class model
  • Evaluate and refine Amazon ML model
  • Use predictions
Who Should Take This Course

IT technologists and hobbyists, computer science students, and domain experts who want to understand the basic principles of Amazon Machine Learning and its application and receive a hands-on practical demonstration of using Amazon Machine Learning. You don’t have to be a data scientist or professional developer to benefit from this course. In fact, small business owners who have a firm handle on their own business data would find value in the examples used, which is a retail business and small dataset.

Course Requirements Familiarity with technology consoles and administrative interfaces would be very helpful. A rudimentary understanding of the Amazon Web Services platform would be a bonus, but not necessary to learn from this course. A basic understanding of how data and its schema is structured digitally would be an asset to understanding the concepts of Machine Learning.

Module Descriptions

Module 1, “Amazon Machine Learning Basics,” discusses understanding how Amazon ML works and how you can frame problem sets. By the end, the first data set will be uploaded.

Module 2, “Amazon Machine Learning Data Architecture,” covers how to set up the source from SQL Server. The data to be downloaded will be provided, so SQL Server does not need to be installed.

In Module 3, “Data and Schema Configuration,” historical sales data is used to predict the future price of an item. “Gotchas” are showcased so a solid starting machine learning model can be built.

Module 4, “Machine Learning Visualization and Modeling,” uses data insights to further refine the model.

Module 5, “Predictions with Amazon Machine Learning,” examines predictions and determining future data. The model’s performance is analyzed, and real-time and batch predictions are applied. Finally, key concepts, questions to consider, and next steps are covered.

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 http://www.informit.com/video.

Table of Contents

  1. Introduction
    1. Amazon Machine Learning: Introduction 00:07:18
  2. Module 1: Amazon Machine Learning Basics
    1. Module introduction 00:00:48
  3. Lesson 1: Introduction
    1. Learning objectives 00:01:35
    2. 1.1 What is Machine Learning? 00:01:30
    3. 1.2 Machine Learning on AWS: Platform Services 00:03:53
    4. 1.3 Machine Learning on AWS: Application Services 00:03:32
    5. 1.4 Who Should Use Amazon ML? 00:02:42
    6. 1.5 What are the Benefits of Machine Learning? 00:01:20
  4. Lesson 2: Which Use Cases Can Amazon ML Solve?
    1. Learning objectives 00:00:44
    2. 2.1 Amazon ML Sample Use Case Walkthrough 00:08:20
  5. Lesson 3: How Does Amazon ML Work?
    1. Learning objectives 00:00:41
    2. 3.1 High Level Overview 00:02:18
    3. 3.2 Options for Data Sources 00:03:20
    4. 3.3 Supervised Machine Learning 00:02:07
    5. 3.4 Unsupervised Machine Learning (Deep Learning) 00:01:14
    6. 3.5 Life Cycle of ML Processing 00:01:28
    7. 3.6 What are the Amazon ML Supervised Machine Learning Algorithms? 00:01:27
  6. Lesson 4: Practical Applications for Machine Learning
    1. Learning objectives 00:00:30
    2. 4.1 Mapping Business Scenarios to ML Solutions 00:05:00
    3. 4.2 Curator Project Sample Business Problem for this Course 00:05:45
    4. 4.3 Best Practices for Selecting a Business Problem 00:03:15
  7. Lesson 5: Interactive Lab: Set up S3 Bucket for Amazon ML Usage
    1. Learning objectives 00:00:36
    2. 5.1 Create and Configure S3 Bucket 00:02:40
  8. Module 2: Amazon Machine Learning Data Architecture
    1. Module introduction 00:00:46
  9. Lesson 6: Information Architecture
    1. Learning objectives 00:00:34
    2. 6.1 What are Features? 00:00:54
    3. 6.2 What is a Target? 00:01:08
    4. 6.3 What are Observations? 00:01:56
    5. 6.4 Labeled vs. Unlabeled Data 00:02:29
    6. 6.5 What is Ground Truth? 00:01:00
    7. 6.6 Best Practices for Input Data 00:02:00
  10. Lesson 7: Interactive Lab: Prepare Data
    1. Learning objectives 00:00:46
    2. 7.1 Where can you get Sample Data? 00:00:48
    3. 7.2 Collect Source Data for a Regression Model 00:08:29
    4. 7.3 Format Requirements for CSV File 00:01:52
    5. 7.4 Examining the CSV File 00:04:11
    6. 7.5 Collect Source Data for a Multi Class Model 00:02:12
  11. Lesson 8: Data Preparation
    1. Learning objectives 00:00:33
    2. 8.1 A Closer Look at the Input Data 00:01:14
    3. 8.2 Interactive Lab: Scrubbing the Data 00:04:08
  12. Module 3: Data and Schema Configuration
    1. Module introduction 00:00:45
  13. Lesson 9: Interactive Lab: Upload Data File to S3
    1. Learning objectives 00:00:42
    2. 9.1 Working with S3 and Amazon ML 00:02:47
  14. Lesson 10: Interactive Lab: Amazon Machine Learning Dashboard
    1. Learning objectives 00:00:33
    2. 10.1 Access Amazon ML with the AWS Console 00:00:51
    3. 10.2 The Amazon ML Dashboard and Region Support 00:02:24
  15. Lesson 11: Interactive Lab: Set up the Datasource
    1. Learning objectives 00:00:31
    2. 11.1 Create a New Datasource 00:00:55
    3. 11.2 Set Permissions and Verify Datasource 00:01:10
  16. Lesson 12: Interactive Lab: Refine Schema
    1. Learning objectives 00:00:34
    2. 12.1 Configuring Schema and Target 00:02:20
    3. 12.2 Finalize and Adjust Schema 00:02:30
  17. Module 4: Machine Learning Visualization and Modeling
    1. Module introduction 00:01:14
  18. Lesson 13: Interactive Lab: Data Insights and Visualization Tools
    1. Learning objectives 00:01:03
    2. 13.1 What are the Benefits of the Data Insights Tool? 00:01:19
    3. 13.2 What can we Examine with the Data Insights Tool? 00:05:21
    4. 13.3 Interactive Lab: Exploring Target Distributions 00:03:58
    5. 13.4 Interactive Lab: Identify Missing Value Distributions 00:04:33
    6. 13.5 Interactive Lab: Identify Invalid Data 00:01:38
    7. 13.6 Interactive Lab: Other Notable Observations 00:01:04
  19. Lesson 14: Interactive Lab: Create a New Amazon ML Model
    1. Learning objectives 00:00:56
    2. 14.1 Create Model from Data Insights Page 00:01:35
    3. 14.2 Configure Model Settings 00:02:17
    4. 14.3 Data Splitting 00:01:56
  20. Lesson 15: Interactive Lab: Model Evaluation and Insights
    1. Learning objectives 00:00:49
    2. 15.1 What Happens in an Evaluation? 00:01:04
    3. 15.2 Model Insights: Evaluation Summary 00:03:48
    4. 15.3 Model Insights: Evaluation Alerts 00:01:41
    5. 15.4 Evaluate Model Performance 00:00:54
  21. Lesson 16: How to Refine a Model
    1. Learning objectives 00:00:44
    2. 16.1 Refining Amazon ML Model Evaluations 00:05:42
    3. 16.2 Decrease / Increase Attributes 00:00:39
    4. 16.3 Create a Custom Recipe 00:01:27
  22. Module 5: Predictions with Amazon Machine Learning
    1. Module introduction 00:01:30
  23. Lesson 17: Predictions
    1. Learning objectives 00:00:23
    2. 17.1 How do Predictions Work? 00:01:05
    3. 17.2 What are the Types of Predictions? 00:01:27
    4. 17.3 Batch and Real-time Predictions 00:02:11
  24. Lesson 18: Interactive Lab: Real-time Predictions
    1. Learning objectives 00:00:57
    2. 18.1 Working with Real-time Predictions 00:03:00
  25. Lesson 19: Interactive Lab: Batch Predictions
    1. Learning objectives 00:00:48
    2. 19.1 Working with Batch Predictions 00:07:03
    3. 19.2 View the Manifest 00:01:25
    4. 19.3 Downloading and Applying Predictions 00:01:44
  26. Lesson 20: Interactive Lab: Around the World with a Multiclass Model
    1. Learning objectives 00:01:29
    2. 20.1 Using Machine Learning to Make Your Business More Powerful 00:03:50
    3. 20.2 Interactive Lab: Extract and Prepare Data 00:00:58
    4. 20.3 Interactive Lab: Create New Datasource and Multiclass Model 00:02:13
    5. 20.4 Interactive Lab: Examine Multiclass Model Summary 00:01:13
    6. 20.5 Understanding how Multiclass Models are Evaluated 00:02:08
    7. 20.6 Interactive Lab: Evaluate Multiclass Model Performance 00:04:21
    8. 20.7 Run Batch Predictions Against a Multiclass Model 00:03:59
  27. Lesson 21: Final Review and Next Steps
    1. Learning objectives 00:00:27
    2. 21.1 Review of Key Concepts 00:01:38
    3. 21.2 Questions to Consider 00:01:09
    4. 21.3 Call to Action 00:01:40
  28. Summary
    1. Amazon Machine Learning: Summary 00:00:29