IT Professional Curricula     Internet and Network Technologies Solution Area     Cloud Computing     DP-100: Designing and Implementing a Data Science Solution on Azure

---

The Azure Machine Learning SDK provides components to quantity the importance of features, identify bias in models, and determine differential privacy. In this course, you'll learn more about these features and how they can be used to increase the quality of your machine learning models.
First, you'll examine how models can use global and local features to quantify the importance of each model feature. You'll explore how model explainers can be created using the Azure Machine Learning SDK and how to visualize the model using the Azure Machine Learning Studio. Next, you'll learn how to use a Jupyter Notebook and Python to generate explanations that are part of a model training experiment. Finally, you'll learn about training model bias and how to analyze model fairness using the Fairlearn Python package to detect and mitigate unfairness in a trained model.
This course is one in a collection that prepares learners for the Designing and Implementing a Data Science Solution on Azure (DP-100) exam.

---

---

Objectives

DP-100 - Azure Data Scientist Associate: Model Features & Differential Privacy discover the key concepts covered in this course describe how learning models can use global and local features to quantify the importance of each feature describe how model explainers can be created using the Azure Machine Learning SDK create an explainer and upload the explanation so it is available later analysis use a Jupyter Notebook and Python to generate explanations that are part of a model training experiment use visualizations in Azure Machine Learning Studio to visualize model explanations describe how training models can be biased due to biases in the training data analyze model fairness using the Fairlearn Python package to identify imbalances between predictions and prediction performance use a Jupyter Notebook and Python to detect and mitigate unfairness in a trained model summarize the key concepts covered in this course