O'Reilly logo
live online training icon Live Online training

AWS Machine Learning Specialty Certification Crash Course

Noah Gift

This course will cover the essentials of Machine Learning on AWS and prepare a candidate to sit for and clear the AWS Machine Learning-Specialty (ML-S) Certification exam. There are four main categories that will be covered: Data Engineering, EDA (Exploratory Data Analysis), Modeling, and Operations. The final portion of the course will be to cover real world case studies of Machine Learning problems on AWS.

What you'll learn-and how you can apply it

  • Learn how to perform Data Engineering tasks on AWS
  • Learn how to use Exploratory Data Analysis (EDA) to solve machine learning problems on AWS
  • Learn how to perform Machine Learning Modeling tasks on the AWS platform
  • Learn how to operationalize Machine Learning models and deploy them to production on the AWS platform
  • Learn how to think about the AWS Machine Learning-Specialty (ML-S) Certification exam to optimize for the best outcome.

This training course is for you because...

  • You are a DevOps Engineer who wants to understand how to operationalize ML workloads.
  • You are a Software Engineer who wants to master Machine Learning terminology, and practices on AWS.
  • You are a Machine Learning Engineer who wants to solidify their your knowledge on AWS Machine Learning practices.
  • You are a Product Manager who needs to understand the AWS Machine Learning lifecycle.
  • You are a Data Scientist who runs Machine Learning workloads on AWS.

Prerequisites

  • 1-2 years of experience with AWS and six months using ML tools. Ideally candidates would have already passed the AWS Cloud Practitioner cert.

Course Set-up

Recommended Preparation

Recommended Follow-up

About your instructor

  • Noah Gift is a lecturer in the University of California, Berkeley, graduate data science program, the Northwestern University graduate data science program, and the MSBA program at the University of California, Davis, Graduate School of Management. He consults with startups and other companies on machine learning and cloud architecture and does CTO-level consulting as the founder of Pragmatic AI Labs. Noah has approximately 20 years’ experience programming in Python and is a Python Software Foundation Fellow. Previously, he worked for a variety of companies in roles such as CTO, general manager, consulting CTO, and cloud architect. He’s published over 100 technical publications, including books on cloud machine learning and DevOps, for O’Reilly, Pearson, DataCamp, Udacity, and other publishers. He’s also a certified AWS Solutions Architect. Noah earned an MBA from the University of California, Davis, an MS in computer information systems from California State University, Los Angeles, and a BS in nutritional science from Cal Poly, in San Luis Obispo. You can find more about Noah by following him on GitHub, visiting his website, or connecting with him on LinkedIn.

Schedule

The timeframes are only estimates and may vary according to how the class is progressing

Day 1

Part 1: AWS Machine Learning-Specialty (ML-S) Certification Length (90 min)

  • Get an overview of the certification
  • Use exam study resources
  • Review the exam guide
  • Learn the exam strategy
  • Learn the best practices of ML on AWS
  • Learn the techniques to accelerate hands-on practice
  • Understand important ML related services

Q&A (15 min)

Break (15 min)

Part 2: Data Engineering for ML on AWS Length (45 min)

  • Learn data ingestion concepts
  • Using data cleaning and preparation
  • Learn data storage concepts
  • Learn ETL solutions (Extract-Transform-Load)
  • Understand data batch vs data streaming
  • Understand data security
  • Learn data backup and recovery concepts

Q&A (10 min)

Break (5 min)

Part 3: Exploratory Data Analysis on AWS Length (45 min)

  • Understand data visualization: Overview
  • Learn Clustering
  • Use Summary Statistics
  • Implement Heatmap
  • Understand Principal Component Analysis (PCA)
  • Understand data distributions
  • Use data normalization techniques

Q&A (15 min)

Day 2

Part 4: Machine Learning Modeling on AWS & Operationalize Machine Learning on AWS Length (90 min)

  • Understand AWS ML Systems: Overview (Sagemaker, AWS ML, EMR, MXNet)
  • Use Feature Engineering
  • Train a Model
  • Evaluate a Model
  • Tune a Model
  • Understand ML Inference
  • Understand Deep Learning on AWS
  • Understand ML operations: Overview
  • Use Containerization with Machine Learning and Deep Learning
  • Implement continuous deployment and delivery for Machine Learning
  • Understand A/B Testing production deployment
  • Troubleshoot production deployment
  • Understand production security
  • Understand cost and efficiency of ML systems

Q&A (15 min)

Break (15 min)

Part 5: Create a Production Machine Learning Application Length (45 min)

  • Create Machine Learning Data Pipeline
  • Perform Exploratory Data Analysis using AWS Sagemaker
  • Create Machine Learning Model using AWS Sagemaker
  • Deploy Machine Learning Model using AWS Sagemaker

Q&A (10 min)

Break (5 min)

Part 6: Case Studies Length (45 min)

  • Sagemaker Features
  • DeepLense Features
  • Kinesis Features
  • AWS Flavored Python
  • Cloud9
  • Key Terminology

Q&A (15 min)