AWS Certified Machine Learning Specialty: MLS-C01 Certification Guide

AWS Certified Machine Learning Specialty: MLS-C01 Certification Guide

by Somanath Nanda, Weslley Moura
Released March 2021
Publisher(s): Packt Publishing
ISBN: 9781800569003

Read it now on the O’Reilly learning platform with a 10-day free trial.

O’Reilly members get unlimited access to books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.

Start your free trial

Book description

Prepare to achieve AWS Machine Learning Specialty certification with this complete, up-to-date guide and take the exam with confidence

Key Features

  • Get to grips with core machine learning algorithms along with AWS implementation
  • Build model training and inference pipelines and deploy machine learning models to the Amazon Web Services (AWS) cloud
  • Learn all about the AWS services available for machine learning in order to pass the MLS-C01 exam

Book Description

The AWS Certified Machine Learning Specialty exam tests your competency to perform machine learning (ML) on AWS infrastructure. This book covers the entire exam syllabus using practical examples to help you with your real-world machine learning projects on AWS.

Starting with an introduction to machine learning on AWS, you'll learn the fundamentals of machine learning and explore important AWS services for artificial intelligence (AI). You'll then see how to prepare data for machine learning and discover a wide variety of techniques for data manipulation and transformation for different types of variables. The book also shows you how to handle missing data and outliers and takes you through various machine learning tasks such as classification, regression, clustering, forecasting, anomaly detection, text mining, and image processing, along with the specific ML algorithms you need to know to pass the exam. Finally, you'll explore model evaluation, optimization, and deployment and get to grips with deploying models in a production environment and monitoring them.

By the end of this book, you'll have gained knowledge of the key challenges in machine learning and the solutions that AWS has released for each of them, along with the tools, methods, and techniques commonly used in each domain of AWS ML.

What you will learn

  • Understand all four domains covered in the exam, along with types of questions, exam duration, and scoring
  • Become well-versed with machine learning terminologies, methodologies, frameworks, and the different AWS services for machine learning
  • Get to grips with data preparation and using AWS services for batch and real-time data processing
  • Explore the built-in machine learning algorithms in AWS and build and deploy your own models
  • Evaluate machine learning models and tune hyperparameters
  • Deploy machine learning models with the AWS infrastructure

Who this book is for

This AWS book is for professionals and students who want to prepare for and pass the AWS Certified Machine Learning Specialty exam or gain deeper knowledge of machine learning with a special focus on AWS. Beginner-level knowledge of machine learning and AWS services is necessary before getting started with this book.

Table of contents

  1. AWS Certified Machine Learning Specialty: MLS-C01 Certification Guide
  2. Contributors
  3. About the authors
  4. About the reviewer
  5. Preface
    1. Who this book is for
    2. What this book covers
    3. To get the most out of this book
    4. Download the example code files
    5. Download the color images
    6. Conventions used
    7. Get in touch
    8. Reviews
  6. Section 1: Introduction to Machine Learning
  7. Chapter 1: Machine Learning Fundamentals
    1. Comparing AI, ML, and DL
      1. Examining ML
      2. Examining DL
    2. Classifying supervised, unsupervised, and reinforcement learning
      1. Introducing supervised learning
    3. The CRISP-DM modeling life cycle
    4. Data splitting
      1. Overfitting and underfitting
      2. Applying cross-validation and measuring overfitting
      3. Bootstrapping methods
      4. The variance versus bias trade-off
      5. Shuffling your training set
    5. Modeling expectations
    6. Introducing ML frameworks
    7. ML in the cloud
    8. Summary
    9. Questions
  8. Chapter 2: AWS Application Services for AI/ML
    1. Technical requirements
    2. Analyzing images and videos with Amazon Rekognition
      1. Exploring the benefits of Amazon Rekognition
      2. Getting hands-on with Amazon Rekognition
    3. Text to speech with Amazon Polly
      1. Exploring the benefits of Amazon Polly
      2. Getting hands-on with Amazon Polly
    4. Speech to text with Amazon Transcribe
      1. Exploring the benefits of Amazon Transcribe
      2. Getting hands-on with Amazon Transcribe
    5. Implementing natural language processing with Amazon Comprehend
      1. Exploring the benefits of Amazon Comprehend
      2. Getting hands-on with Amazon Comprehend
    6. Translating documents with Amazon Translate
      1. Exploring the benefits of Amazon Translate
      2. Getting hands-on with Amazon Translate
    7. Extracting text from documents with Amazon Textract
      1. Exploring the benefits of Amazon Textract
      2. Getting hands-on with Amazon Textract
    8. Creating chatbots on Amazon Lex
      1. Exploring the benefits of Amazon Lex
      2. Getting hands-on with Amazon Lex
    9. Summary
      1. Questions
      2. Answers
  9. Section 2: Data Engineering and Exploratory Data Analysis
  10. Chapter 3: Data Preparation and Transformation
    1. Identifying types of features
    2. Dealing with categorical features
      1. Transforming nominal features
      2. Applying binary encoding
      3. Transforming ordinal features
      4. Avoiding confusion in our train and test datasets
    3. Dealing with numerical features
      1. Data normalization
      2. Data standardization
      3. Applying binning and discretization
      4. Applying other types of numerical transformations
    4. Understanding data distributions
    5. Handling missing values
    6. Dealing with outliers
    7. Dealing with unbalanced datasets
    8. Dealing with text data
      1. Bag of words
      2. TF-IDF
      3. Word embedding
    9. Summary
    10. Questions
  11. Chapter 4: Understanding and Visualizing Data
    1. Visualizing relationships in your data
    2. Visualizing comparisons in your data
    3. Visualizing distributions in your data
    4. Visualizing compositions in your data
    5. Building key performance indicators
    6. Introducing Quick Sight
    7. Summary
    8. Questions
  12. Chapter 5: AWS Services for Data Storing
    1. Technical requirements
    2. Storing data on Amazon S3
      1. Creating buckets to hold data
      2. Distinguishing between object tags and object metadata
    3. Controlling access to buckets and objects on Amazon S3
      1. S3 bucket policy
    4. Protecting data on Amazon S3
      1. Applying bucket versioning
      2. Applying encryption to buckets
    5. Securing S3 objects at rest and in transit
    6. Using other types of data stores
    7. Relational Database Services (RDSes)
    8. Managing failover in Amazon RDS
    9. Taking automatic backup, RDS snapshots, and restore and read replicas
    10. Writing to Amazon Aurora with multi-master capabilities
    11. Storing columnar data on Amazon Redshift
    12. Amazon DynamoDB for NoSQL database as a service
    13. Summary
      1. Questions
      2. Answers
  13. Chapter 6: AWS Services for Data Processing
    1. Technical requirements
    2. Creating ETL jobs on AWS Glue
      1. Features of AWS Glue
      2. Getting hands-on with AWS Glue data catalog components
      3. Getting hands-on with AWS Glue ETL components
    3. Querying S3 data using Athena
    4. Processing real-time data using Kinesis data streams
    5. Storing and transforming real-time data using Kinesis Data Firehose
    6. Different ways of ingesting data from on-premises into AWS
      1. AWS Storage Gateway
      2. Snowball, Snowball Edge, and Snowmobile
      3. AWS DataSync
    7. Processing stored data on AWS
      1. AWS EMR
      2. AWS Batch
    8. Summary
      1. Questions
      2. Answers
  14. Section 3: Data Modeling
  15. Chapter 7: Applying Machine Learning Algorithms
    1. Introducing this chapter
    2. Storing the training data
    3. A word about ensemble models
    4. Supervised learning
      1. Working with regression models
      2. Working with classification models
      3. Forecasting models
      4. Object2Vec
    5. Unsupervised learning
      1. Clustering
      2. Anomaly detection
      3. Dimensionality reduction
      4. IP Insights
    6. Textual analysis
      1. Blazing Text algorithm
      2. Sequence-to-sequence algorithm
      3. Neural Topic Model (NTM) algorithm
    7. Image processing
      1. Image classification algorithm
      2. Semantic segmentation algorithm
      3. Object detection algorithm
    8. Summary
    9. Questions
  16. Chapter 8: Evaluating and Optimizing Models
    1. Introducing model evaluation
    2. Evaluating classification models
      1. Extracting metrics from a confusion matrix
      2. Summarizing precision and recall
    3. Evaluating regression models
      1. Exploring other regression metrics
    4. Model optimization
      1. Grid search
    5. Summary
    6. Questions
  17. Chapter 9: Amazon SageMaker Modeling
    1. Technical requirements
    2. Creating notebooks in Amazon SageMaker
      1. What is Amazon SageMaker?
      2. Getting hands-on with Amazon SageMaker notebook instances
      3. Getting hands-on with Amazon SageMaker's training and inference instances
    3. Model tuning
      1. Tracking your training jobs and selecting the best model
    4. Choosing instance types in Amazon SageMaker
      1. Choosing the right instance type for a training job
      2. Choosing the right instance type for an inference job
    5. Securing SageMaker notebooks
    6. Creating alternative pipelines with Lambda Functions
      1. Creating and configuring a Lambda Function
      2. Completing your configurations and deploying a Lambda Function
    7. Working with Step Functions
    8. Summary
      1. Questions
      2. Answers
    9. Why subscribe?
  18. Other Books You May Enjoy
    1. Packt is searching for authors like you
    2. Leave a review - let other readers know what you think

Product information

  • Title: AWS Certified Machine Learning Specialty: MLS-C01 Certification Guide
  • Author(s): Somanath Nanda, Weslley Moura
  • Release date: March 2021
  • Publisher(s): Packt Publishing
  • ISBN: 9781800569003