Machine Learning Pipeline on AWS
In this 4-day training, you’ll learn about each stage of the pipeline through instructor presentations and demonstrations, and then apply that knowledge to complete a project that solves 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 to solve the selected business problem.
COD: AW-ML-PIPE
Categorie: AWS
Who should participate
- Developers
- Solution architects
- Data engineers
- Anyone with little or no ML experience and wants to learn about the ML pipeline using Amazon SageMaker
Prerequisites
- Basic knowledge of the Python programming language
- Basic knowledge of AWS cloud infrastructure (Amazon S3 and Amazon CloudWatch)
- Basic experience working in a Jupyter notebook environment
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 on AWS.
- Apply machine learning to a real business problem upon completion of the course
Day 1
Module 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 the course projects and approach
Module 2: Introduction to Amazon SageMaker
- Introduction to Amazon SageMaker
- Demo: Amazon SageMaker e i notebook Jupyter
- Practice: Amazon SageMaker and Jupyter Notebooks
Day 2
Module 3: Formulation of the problem
- Overview of problem formulation and the decision if ML is the right solution
- Converting a business problem to an ML problem
- Demo: Amazon SageMaker Ground Truth
- Pratica: Amazon SageMaker Ground Truth
- Practice problem solving
- Formulate problems for projects
Module 4: Preprocessing
- Overview of data collection and integration, and data preprocessing and visualization techniques.
- Practice preprocessing
- Preprocessing of project data
- Class discussion about projects
Day 3
Module 5: Model training
- Choosing the right algorithm
- Formatting and splitting data for training
- Loss and gradient descent functions to improve the model
- Demonstration: Creating a training job in Amazon SageMaker
Module 6: Model evaluation
- How to evaluate classification models
- How to evaluate regression models
- Model training and evaluation exercises
- Training and evaluation of project models
- Initial presentations of the project
Day 4
Module 7: Feature engineering and model tuning
- Extraction, selection, creation and transformation of features
- Adjustment of hyperparameters
- Demonstration: SageMaker hyperparameter tuning
- Practice feature engineering and model tuning
- Applying feature engineering and model tuning to projects
- Presentation of the final project
Module 8: Distribution
- How to deploy, inference, and monitor your model on Amazon SageMaker
- Deploying ML to the margins
- Demonstration: Creating an Amazon SageMaker endpoint
- Later evaluation
Duration – 4 days
Delivery – in Classroom, On Site, Remote
PC and SW requirements:
- Internet connection
- Web browser, Google Chrome
- Zoom
Language
Instructor: English
Workshop: English
Slides: English
