Overview

This course features Coursera Coach! A smarter way to learn with interactive, real-time conversations that help you test your knowledge, challenge assumptions, and deepen your understanding as you progress through the course. In this course, you'll gain hands-on experience with AWS SageMaker Canvas, a powerful no-code tool for machine learning. You'll start by understanding the basics of machine learning and Amazon Web Services (AWS), laying a solid foundation for the rest of the course. As you progress, you'll explore how SageMaker Canvas simplifies building, training, and deploying machine learning models with no coding required. Throughout the course, you'll complete four projects that cover real-world applications such as banknote authentication, spam SMS detection, customer churn prediction, and wine quality prediction. These projects will guide you through adding training data, building models, making predictions, and validating accuracy. The hands-on experience will deepen your understanding and help you master SageMaker Canvas' interface and capabilities. By the end of the course, you'll be able to apply your skills to a variety of machine learning tasks using SageMaker Canvas. This course is ideal for individuals who are new to machine learning or those looking to streamline the process of building machine learning models without writing code.

Syllabus

Introduction to Machine Learning

In this module, we will introduce the basics of machine learning, covering fundamental concepts and applications. You will gain an understanding of what machine learning is and how it works, setting the foundation for the rest of the course.

Introduction to AWS

In this module, we will explore Amazon Web Services (AWS), the platform that powers SageMaker Canvas. You’ll learn what AWS is, its key services, and how to sign in to the AWS console for cloud-based machine learning activities.

Introduction to SageMaker

In this module, we will dive into Amazon SageMaker, a powerful tool for building and training machine learning models. You’ll also get introduced to SageMaker Canvas, the no-code interface that enables you to create models without needing programming skills.

Setup

In this module, we will walk through setting up your SageMaker domain and user environment. Additionally, you'll learn how to configure data in S3 Buckets, ensuring everything is ready for building machine learning models in SageMaker.

SageMaker Canvas Interface Walkthrough

In this module, we will explore the SageMaker Canvas interface, guiding you through its various features and functionalities. This walkthrough will help you efficiently navigate and use SageMaker Canvas for machine learning tasks.

Project 1 - Banknote Authentication

In this module, we will apply what we've learned to build a model for banknote authentication. You'll gather training data, build a predictive model, and validate its performance through batch prediction and accuracy testing.

Project 2 - Spam SMS Detection

In this module, we will focus on detecting spam SMS messages using machine learning. You’ll learn how to prepare your data, build a model, and evaluate its predictions to ensure it accurately detects spam.

Project 3 - Customer Churn Prediction

In this module, we will predict customer churn using machine learning. You'll import relevant customer data, build a predictive model, and assess its ability to forecast churn rates accurately.

Project 4 - Wine Quality Prediction

In this module, we will create a model to predict wine quality. You will work with datasets, build a model, and test its performance, learning how to combine multiple data sources for better results.

Assignment

In this module, you will complete an assignment where you predict white wine quality. This hands-on exercise will reinforce your learning and improve your ability to apply machine learning techniques using SageMaker Canvas.

Other Important Features in SageMaker Canvas

In this module, we will cover the versioning feature in SageMaker Canvas. You'll learn how to manage different versions of your models, ensuring you can track changes and improvements over time.

Congratulations and Next Steps

In this module, we will conclude the course with tips on obtaining more datasets, getting help with SageMaker Canvas, and congratulating you on completing the course. You'll also receive guidance on your next steps in mastering no-code machine learning.