Automated Machine Learning significantly reduces the amount of time and skill required to develop a production-ready model. It rapidly iterates over the various combinations of algorithms and hyperparameters and provides a recommendation on the most optimal model for a given dataset. Automated ML is based on breakthrough research from the Microsoft Research division. Experiments can be processed on various different types of computing resources such as Virtual Machines and Kubernetes that can either be local or in the cloud.
In this lab, you will create a predictive classification model with Azure's Automated Machine Learning service to quickly discover the most optimal model for a dataset.
Learning Objectives
Upon completion of this lab you will be able to:
- Create an AutoML run in Azure Machine Learning Studio
- Discover the most optimal model to use for a particular dataset
Lab Prerequisites
You should be familiar with:
- Basic concepts of Azure Machine Learning
- Experience with Python is not required
Updates
December 14th, 2022 - Updated instructions & screenshots to reflect latest UI
Luke is a Site Reliability Engineer at Microsoft. His background is infrastructure development using Terraform and in 2021 he was awarded the HashiCorp Ambassador award. He is an Azure DevOps Engineer Expert, Azure Administrator Associate, and HashiCorp Certified - Terraform Associate.