Microsoft Certified: Azure Data Scientist Associate (DP100)

In this three-day Microsoft certified course, students will learn how to operate machine learning solutions at cloud scale using Azure Machine Learning. This course teaches you to leverage your existing knowledge of Python and machine learning to manage data ingestion and preparation, model training and deployment, and machine learning solution monitoring in Microsoft Azure.

This training is a comprehensive preparation for the DP-100: Designing and Implementing a Data Science Solution on Azure exam to earn the Microsoft Certified: Azure Data Scientist Associate certification.

Module 1: Introduction to the Azure Machine Learning SDK

• Azure Machine Learning workspaces
• Azure Machine Learning tools and interfaces
• Azure Machine Learning experiments

Module 2: Use Automated Machine Learning in Azure Machine Learning

• What is machine learning?
• What is Azure Machine Learning studio?
• What is Azure Automated Machine Learning?
• Understand the AutoML process

Module 3: Create a classification model with Azure Machine Learning designer

• Identify classification machine learning scenarios
• What is Azure Machine Learning?
• What is Azure Machine Learning designer?
• Understand steps for classification

Module 4: Train a machine learning model with Azure Machine Learning

• Run a training script
• Using script parameters
• Registering models

Module 5: Work with Data in Azure Machine Learning

• Introduction to datastores
• Use datastores
• Introduction to datasets
• Use datasets

Module 6: Work with Compute in Azure Machine Learning

• Introduction to environments
• Introduction to compute targets
• Create compute targets
• Use compute targets

Module 7: Orchestrate machine learning with pipelines

• Introduction to pipelines
• Pass data between pipeline steps
• Reuse pipeline steps
• Publish pipelines
• Use pipeline parameters
• Schedule pipelines

Module 8: Deploy real-time machine learning services with Azure Machine Learning

• Deploy a model as a real-time service
• Consume a real-time inferencing service
• Troubleshoot service deployment

Module 9: Deploy batch inference pipelines with Azure Machine Learning

• Creating a batch inference pipeline
• Publishing a batch inference pipeline

Module 10: Tune hyperparameters with Azure Machine Learning

• Defining a search space
• Configuring sampling
• Configuring early termination
• Running a hyperparameter tuning experiment

Module 11: Automate machine learning model selection with Azure Machine Learning

• Automated machine learning tasks and algorithms
• Preprocessing and featurization
• Running automated machine learning experiments

Module 12: Explore differential privacy

• Understand differential privacy
• Configure data privacy parameters

Module 13: Explain machine learning models with Azure Machine Learning

• Feature importance
• Using explainers
• Creating explanations
• Visualizing explanations

Module 14: Detect and mitigate unfairness in models with Azure Machine Learning

• Consider model fairness
• Analyze model fairness with Fairlearn
• Mitigate unfairness with Fairlearn

Module 15: Monitor data drift with Azure Machine Learning

• Creating a data drift monitor
• Scheduling alerts

Module 16: Monitor models with Azure Machine Learning

• Enable Application Insights
• Capture and view telemetry