AZURE-5

IN PROGRESS

dATA SCIENCE

Module 1: Doing Data Science on Azure

Module Objectives:

  • Explain the steps involved in the Data Science Process
  • Explain the machine learning modeling cycle
  • Explain data cleansing and preparation
  • Explain model feature engineering
  • Explain model training and evaluation
  • Explain about model deployment
  • Understand the specialized roles in the data science process

Module 2: Doing Data Science with Azure Machine Learning service

Module Objectives:

  • Explain the difference between Azure Machine Learning Studio and Azure Machine Learning service
  • Explain how Azure Machine Learning service fits into the data science process
  • Explain the concepts related to an Azure Machine Learning service experiment
  • Explain the Azure Machine Learning service pipeline
  • Train a model using Azure Machine Learning service

Module 3: Automate Model Selection with AML Service

Module Objectives:

  • Explain the machine learning pipeline
  • Explain Azure Machine Learning service AutoML
  • Create a Python script that uses the Azure Machine Learning service’s AutoML to recommend a model
  • Test the recommended model from your Python script

Module 4: Manage and Monitor Models

Module Objectives:

  • Register a model in the Azure Machine Learning service Model Registry
  • Query information about the registered model
  • Register an image containing a machine learning model
  • Install the Azure ML Monitoring SDK
  • Enable model data collection using the portal and using Python with the SDK
  • Use the Azure ML Monitoring SDK to collect and monitor model data

 

Module 1: Doing Data Science on Azure

Module Objectives:

  • Explain the steps involved in the Data Science Process
  • Explain the machine learning modeling cycle
  • Explain data cleansing and preparation
  • Explain model feature engineering
  • Explain model training and evaluation
  • Explain about model deployment
  • Understand the specialized roles in the data science process