Course Version

This course outline applies to version 1.0 of AWS Academy Machine Learning Foundations in English.

Description

AWS Academy Machine Learning Foundations introduces students to the concepts and terminology of Artificial Intelligence and machine learning. By the end of this course, students will be able to select and apply machine learning services to resolve business problems. They will also be able to label, build, train, and deploy a custom machine learning model through a guided, hands-on approach.

Course Objectives

Upon completion of this course, students will be able to:

• Describe machine learning (ML)
• Implement a machine learning pipeline using Amazon SageMaker
• Use managed Amazon ML services for forecasting
• Use managed Amazon ML services for computer vision
• Use managed Amazon ML services for natural language processing

Duration

Approximately 20 hours when delivered synchronously by an educator.

Intended Audience

This introductory course is intended for students at AWS Academy member institutions interested in pursuing a career in data science, ML, and AI.

Student Prerequisites

To ensure success in this course, students should have:

• Completed AWS Academy Cloud Foundations (or another introductory cloud computing course)
• Experience scripting with Python or equivalent
• A basic understanding of statistics

Delivery Methods

This course can be delivered in person with synchronous lectures or with digital training modules that students can complete independently, or a combination of in-person and digital instruction (flipped- classroom model).

Educator Prerequisites

This course does not have any prerequisites for educators. However, prior to facilitating this course, educators are recommended to complete this course, complete the AWS Academy Cloud Foundations course, and pass the AWS Certified Cloud Practitioner exam.

Learning Resources

• Lecture materials
• Online multiple-choice knowledge checks
• Lab exercises
• Digital training
• Lecture or video introductions
• Lecture or video demos
• Example solutions
• S documentation and frameworks

Course Contents

		# Slides/ Lecture & Demo Duration	Lab Duration	Total Duration
Module 1 – Welcome to AWS Academy Machine Learning Foundations		21/30 min.		30 min.
Lecture or Video	Course prerequisites and objectives
Lecture or Video	Machine learning job roles
Lecture or Video	Resources, documentation, and whitepapers
Module 2 – Introducing Machine Learning		48/120 min.		120 min.
Lecture or Video	What is Machine Learning?
Lecture or Video	Business problems solved with Machine Learning
Lecture or Video	Machine Learning process

		# Slides/ Lecture & Demo Duration	Lab Duration	Total Duration
Lecture or Video	Machine Learning tools overview
Lecture or Video	Machine Learning challenges
Demo	Demonstration: Introducing Amazon SageMaker	10 min.
Knowledge Check	Machine Learning Concepts	10 min.
Module 3 – Implementing a Machine Learning pipeline with Amazon SageMaker		132/230 min.	200 min.	430 min.
Lecture or Video	Scenario introduction
Lecture or Video	Collecting and securing data
Guided Lab	Exploring Amazon SageMaker		30 min.
Lecture or Video	Evaluating your data
Guided Lab	Visualizing Data		30 min.
Lecture or Video	Feature engineering
Guided Lab	Encoding Categorical Variables		30 min.
Lecture or Video	Training
Demo	Demonstration: Training a Model Using Amazon SageMaker	10 min.
Guided Lab	Splitting Data and Training a Model using XGBoost		30 min.
Lecture or Video	Hosting and using the model
Guided Lab	Hosting and Consuming a Model on AWS		20 min.

		# Slides/ Lecture & Demo Duration	Lab Duration	Total Duration
Lecture or Video	Evaluating the accuracy of the model
Guided Lab	Evaluating Model Accuracy		30 min.
Lecture or Video	Hyperparameter and model tuning
Demo	Demonstration: Optimizing Amazon SageMaker Hyperparameters	10 min.
Demo	Demonstration: Running Amazon SageMaker Autopilot	10 min.
Guided Lab	Tuning with Amazon SageMaker		30 min.
Knowledge Check	Machine Learning pipeline implementation	10 min.
Challenge Lab 1 Class Project – Select and Train an algorithm			300 min.	300 min.
Module 4 – Introducing Forecasting		38/60 min.	60 min.	120 min.
Lecture or Video	Forecasting overview
Lecture or Video	Processing time series data
Lecture or Video	Using Amazon Forecast
Demo	Demonstration: Creating a Forecast with Amazon Forecast	10 min.
Guided Lab	Creating a Forecast with Amazon Forecast		60 min.
Knowledge Check	Managed Services for Forecasting	10 min.
Module 5 – Introducing Computer Vision (CV)		56/60 min.	60 min.	120 min.
Lecture or Video	Introducing Computer Vision

		# Slides/ Lecture & Demo Duration	Lab Duration	Total Duration
Lecture or Video	Analyzing image and video
Demo	Demonstration: Introducting Amazon Rekognition	10 min.
Lecture or Video	Preparing custom datasets for computer vision
Demo	Demonstration: Labeling images with Amazon Ground Truth	10 min.
Guided Lab	Facial Recognition		60 min.
Knowledge Check	Computer Vision	10 min.
Module 6 – Introducing Natural Language Processing		37/ 60 min.	60 min.	120 min.
Lecture or Video	Overview of Natural Language Processing
Lecture or Video	Natural Language Processing managed services
Demo	Demonstration: Introducing Amazon Polly	10 min.
Demo	Demonstration: Introducing Amazon Comprend	10 min.
Demo	Demonstration: Introducing Amazon Translate	10 min.
Guided Lab	Create a bot to schedule appointments		60 min.
Knowledge Check	Natural Language Processing	10 min.
Module 7 – Course Wrap-Up		11/ 30 min.		30 min.

		# Slides/ Lecture & Demo Duration	Lab Duration	Total Duration
Lecture or Video	Course summary
Lecture or Video	AWS documentation
Lecture or Video	AWS Certified Machine Learning – Specialty

Module Objectives

Module Title	Learning Objectives
Module 1: Welcome to AWS Academy Machine Learning Foundations	Identify course prerequisites and objectivesDescribe the various roles that require machine learning knowledgeIdentify resources for further learning
Module 2: Introducing Machine Learning	Recognize how machine learning and deep learning are part of artificial intelligenceDescribe artificial intelligence and machine learning terminologyIdentify how machine learning can be used to solve a business problemDescribe the machine learning processList the tools available to data scientistsIdentify when to use machine learning instead of traditional software development methods
Module 3: Implementing a Machine Learning pipeline with Amazon SageMaker	Formulate a problem from a business requestObtain and secure data for machine learning (ML)Build a Jupyter Notebook using Amazon SageMakerOutline the process for evaluating dataExplain why dataneeds to be preprocessedUse open source tools to examine and preprocess dataUse Amazon SageMaker to train and host an ML modelUse cross-validation to test the performance of an ML modelUse a hosted model for inferenceCreate an Amazon SageMaker hyperparameter tuning job to optimize a model’s effectiveness
Module 4:	Describe the business problems solved by using Amazon Forecast

Introducing Forecasting	Describe the challenges of working with time series dataList the steps that are required to create a forecast by using Amazon ForecastUse Amazon Forecast to make a prediction
Module 5: Introducing Computer Vision	Describe the computer vision use casesDescribe the AWS managed machine learning (ML) services for image and video analysisList the steps required to prepare a custom dataset for object detectionDescribe how Amazon SageMaker Ground Truth can be used to prepare a custom datasetUse Amazon Rekognition to perform facial detection
Module 6: Introducing Natural Language Processing	Describe the natural language processing (NLP) use cases that are solved by using managed Amazon ML servicesDescribe the managed Amazon ML services available for NLPUse managed Amazon ML Services
Module 7: Course Wrap-Up	N/A