Information Technology

The Machine Learning Pipeline on AWS

Instructor-Led 9 Agenda

Description

This course explores how to use the machine learning (ML) pipeline to solve a real business problem in a project-based learning environment. Students will learn about each phase of the pipeline from instructor presentations and demonstrations and then apply that knowledge to complete a project solving one of three business problems: fraud detection, recommendation engines, or flight delays. By the end of the course, students will have successfully built, trained, evaluated, tuned, and deployed an ML model using Amazon SageMaker that solves their selected business problem.

Course Overview

Course Objective

In this course, you will learn to: Select and justify the appropriate ML approach for a given business problem Use the ML pipeline to solve a specific business problem Train, evaluate, deploy, and tune an ML model using Amazon SageMaker Describe some of the best practices for designing scalable, cost-optimized, and secure ML pipelines in AWS Apply machine learning to a real-life business problem after the course is complete

Who Should Attend

This course is intended for: Developers Solutions Architects Data Engineers Anyone with little to no experience with ML and wants to learn about the ML pipeline using Amazon SageMaker

Module 0: Introduction Lesson Id 1

Module 0: Introduction

Module 1: Introduction to Machine Learning and the ML Pipeline Lesson Id 2

Module 1: Introduction to Machine Learning and the ML Pipeline

Module 2: Introduction to Amazon SageMaker Lesson Id 3

Module 2: Introduction to Amazon SageMaker

Module 3: Problem Formulation Lesson Id 4

Module 3: Problem Formulation

Module 4: Preprocessing Lesson Id 5

Module 4: Preprocessing

Module 5: Model Training Lesson Id 6

Module 5: Model Training

Module 7: Feature Engineering and Model Tuning Lesson Id 8

Module 7: Feature Engineering and Model Tuning

Module 8: Deployment Lesson Id 9

Module 8: Deployment

Module 6: Model Evaluation Lesson Id 7

Module 6: Model Evaluation

Lesson Id	Title	Description
1	Module 0: Introduction	Pre-assessment
2	Module 1: Introduction to Machine Learning and the ML Pipeline	Overview of machine learning, including use cases, types of machine learning, and key concepts<br />Overview of the ML pipeline<br />Introduction to course projects and approach
3	Module 2: Introduction to Amazon SageMaker	Introduction to Amazon SageMaker<br />Demo: Amazon SageMaker and Jupyter notebooks<br />Hands-on: Amazon SageMaker and Jupyter notebooks
4	Module 3: Problem Formulation	Overview of problem formulation and deciding if ML is the right solution<br />Converting a business problem into an ML problem<br />Demo: Amazon SageMaker Ground Truth<br />Hands-on: Amazon SageMaker Ground Truth<br />Practice problem formulation<br />Formulate problems for projects
5	Module 4: Preprocessing	Overview of data collection and integration, and techniques for data preprocessing and visualization<br />Practice preprocessing<br />Preprocess project data<br />Class discussion about projects
6	Module 5: Model Training	Choosing the right algorithm<br />Formatting and splitting your data for training<br />Loss functions and gradient descent for improving your model<br />Demo: Create a training job in Amazon SageMaker
8	Module 7: Feature Engineering and Model Tuning	Feature extraction, selection, creation, and transformation<br />Hyperparameter tuning<br />Demo: SageMaker hyperparameter optimization<br />Practice feature engineering and model tuning<br />Apply feature engineering and model tuning to projects<br />Final project presentations
9	Module 8: Deployment	How to deploy, inference, and monitor your model on Amazon SageMaker<br />Deploying ML at the edge<br />Demo: Creating an Amazon SageMaker endpoint<br />Post-assessment<br />Course wrap-up
7	Module 6: Model Evaluation	How to evaluate classification models<br />How to evaluate regression models<br />Practice model training and evaluation<br />Train and evaluate project models<br />Initial project presentations