This course explores how to use the machine learning (ML) pipeline to solve a real business problem in a project-based learning environment.  Learn how to use the machine learning (ML) pipeline with Amazon SageMaker with hands-on exercises and four days of instruction. You will learn how to frame your business problems as ML problems and use Amazon SageMaker to train, evaluate, tune, and deploy ML models. Hands-on learning is a key component of this course, so you’ll choose a project to work on, and then apply the knowledge and skills you learn to your chosen project in each phase of the pipeline. You’ll have a choice of projects: fraud detection, recommendation engines, or flight delays.

Course Objectives:

• 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 in 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

Course Outline:

Part 1: Introduction to Machine Learning and the ML Pipeline

1. Overview of machine learning, including use cases, types of machine learning, and key concepts
2. Overview of the ML pipeline
3. Introduction to course projects and approach

Part 2: Introduction to Amazon SageMaker

1. Introduction to Amazon SageMaker
2. Demo: Amazon SageMaker and Jupyter notebooks
3. Lab 1: Introduction to Amazon SageMaker

Part 3: Problem Formulation

1. Overview of problem formulation and deciding if ML is the right solution
2. Converting a business problem into an ML problem
3. Demo: Amazon SageMaker Ground Truth
4. Hands-on: Amazon SageMaker Ground Truth
5. Problem Formulation Exercise and Review
6. Project work for Problem Formulation

Part 4: Preprocessing

1. Overview of data collection and integration, and techniques for data preprocessing and visualization
2. Lab 2: Data Preprocessing (including project work)

Part 5: Model Training

1. Choosing the right algorithm
2. Formatting and splitting your data for training
3. Loss functions and gradient descent for improving your model
4. Demo: Create a training job in Amazon SageMaker

Part 6: Model Training

1. How to evaluate classification models
2. How to evaluate regression models
3. Practice model training and evaluation
4. Train and evaluate project models
5. Lab 3: Model Training and Evaluation (including project work)
6. Project Share-Out 1

Part 7: Feature Engineering and Model Tuning

1. Feature extraction, selection, creation, and transformation
2. Hyperparameter tuning
3. Demo: SageMaker hyperparameter optimization
4. Lab 4: Feature Engineering (including project work)

Part 8: Module Deployment

1. How to deploy, inference, and monitor your model on Amazon SageMaker
2. Deploying ML at the edge

Part 9: Course Wrap-Up

1. Project Share-Out 2
2. Post-Assessment
3. Wrap-up