The Machine Learning Pipeline on AWS

Participants will learn about the individual phases of the pipeline through presentations and demonstrations by the trainers and will apply this knowledge to implement a project to solve one of three business problems: fraud detection, recommendation engines, or flight delays. By the end of the course, participants will have successfully created, trained, evaluated, tuned, and deployed an ML model with Amazon SageMaker that solves their chosen business problem.

1. Introduction to Machine Learning and the ML Pipeline

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

2. Introduction to Amazon SageMaker

• Introduction to Amazon SageMaker
• Demo: Amazon SageMaker and Jupyter Notebooks
• Hands-on: Amazon SageMaker and Jupyter Notebooks

3. Problem Formulation

• Overview of problem formulation and deciding if ML is the right solution
• Transforming a business problem into an ML problem
• Demo: Amazon SageMaker Ground Truth
• Hands-on: Amazon SageMaker Ground Truth
• Practicing problem formulation
• Formulating problems for projects

4. Preprocessing

• Overview of data collection and integration, techniques for data preprocessing and visualization
• Practicing preprocessing
• Preprocessing project data
• Class discussion on projects

5. Model Training

• Selecting the right algorithm
• Formatting and splitting your data for training
• Loss functions and gradient methods for improving your model
• Demo: Creating a training job in Amazon SageMaker

6. Model Evaluation

• Evaluating classification models
• Evaluating regression models
• Hands-on model training and evaluation
• Training and evaluating project models
• Initial project presentations

7. Feature Engineering and Model Tuning

• Feature extraction, selection, creation, and transformation
• Hyperparameter tuning
• Demo: SageMaker hyperparameter optimization
• Practicing feature engineering and model tuning
• Applying feature engineering and model tuning to projects
• Final project presentations

8. Deployment

• Deploying, inferring, and monitoring your model on Amazon SageMaker
• Edge deployment of ML
• Demo: Creating an Amazon SageMaker endpoint
• Post-assessment
• Course wrap-up