DP-100: Designing and Implementing a Data Science Solution on Azure

Classification is a kind of machine learning used to categorize items into classes.

Deep learning is an advanced form of machine learning that emulates the way the human brain learns through networks of connected neurons.

Clustering is a kind of machine learning that is used to group similar items into clusters.

Regression is a commonly used kind of machine learning for predicting numeric values.

Data exploration and analysis is at the core of data science. Data scientists require skills in languages like Python to explore, visualize, and manipulate data.

Machine learning models can often encapsulate unintentional bias that results in unfairness. With Fairlearn and Azure Machine Learning, you can detect and mitigate unfairness in your models.

Introduction to Azure Machine Learning

Learn how to use Azure Machine Learning to train a model and register it in a workspace.

Learn how to work with datastores and datasets in Azure Machine Learning.

Learn how to manage compute contexts for experiments in Azure Machine Learning.

Create pipelines in Azure Machine Learning

Learn how to register and deploy ML models with the Azure Machine Learning service.

Learn how to use automated machine learning in Azure Machine Learning to find the best model for your data.

Explore differential privacy

Changing trends in data over time can reduce the accuracy of the predictions made by a model. Monitoring for this data drift is an important way to ensure your model continues to predict accurately.

After a machine learning model has been deployed into production, it’s important to understand how it is being used by capturing and viewing telemetry.

Many decisions made by organizations and automated systems today are based on predictions made by machine learning models. It’s increasingly important to be able to understand the factors that influence the predictions models make.

Choosing optimal hyperparameter values for model training can be difficult, and usually involved a great deal of trial and error. With Azure Machine Learning, you can leverage cloud-scale experiments to tune hyperparameters.

Machine learning models are often used to generate predictions from large numbers of observations in a batch process. To accomplish this, you can use Azure Machine Learning to publish a batch inference pipeline.

Training a machine learning model is an iterative process that requires time and compute resources. Automated machine learning can help make it easier.

Regression is a supervised machine learning technique used to predict numeric values. Learn how to create regression models using Azure Machine Learning designer.

Classification is a supervised machine learning technique used to predict categories or classes. Learn how to create classification models using Azure Machine Learning designer.

Clustering is an unsupervised machine learning technique used to group similar entities based on their features. Learn how to create clustering models using Azure Machine Learning designer.

You learn about the types of Azure Data Science Virtual Machines (DSVM) and when to use each type. You will learn about the Windows-based and Linux-based DSVMs which each support different needs.

Provision and use an Azure Data Science Virtual Machine

Azure provides some pre-configured virtual machine images specifically designed for data science. Learn how you can use these to get a jump start on your data science work.

Create an Azure Notebook and use three popular Python libraries to analyze climate data collected by NASA, then share it.

Import airline arrival data into a Jupyter notebook and use Pandas to clean it. Then, build a machine learning model with Scikit-Learn and use Matplotlib to visualize output.

Keras is a high-level neural networks API, written in Python, that runs on top of other deep learning tools such as TensorFlow. This module uses Keras to build a neural network that scores text, such as user reviews for sentiment.