Microsoft Certified: Azure Data Scientist Associate Journey

Machine Learning uses real data to train algorithms that can be used for anomaly detection, computer vision, and natural language processing. In this course, you'll learn about datasets and how to manipulate data for them. Next, you'll learn the difference between labeled and unlabeled data and why some AI models require labeled data. You'll examine the features that should be used for a selected dataset. Next, you'll learn about the types of machine learning algorithms that are available, including regression algorithms, classification algorithms, and clustering algorithms. Finally, you'll explore the difference between supervised and unsupervised machine learning models. This course is one in a collection that prepares learners for the Designing and Implementing a Data Science Solution on Azure (DP-100) exam.

Azure Machine Learning Studio can be used to create and train machine learning models. Support is provided for multiple development tools, programming languages such as Python and R, and numerous machine learning frameworks. In this course, you'll learn about the services provided by the Azure Machine Learning Studio, how to create an Azure account, and how to register and signup to use Azure Machine Learning Studio. You'll also explore available Azure Machine Learning Studio components, which can be used to create machine learning workflows, ingest data from an Azure Blob storage resource, create and use an Azure Machine Learning workspaces, and create and use a compute resource. This course is one in a collection that prepares learners for the Designing and Implementing a Data Science Solution on Azure (DP-100) exam.

Machine learning regression models are used to predict numeric labels for the features of an item. In this course, you'll learn more about using regression models in the Azure Machine Learning Studio. First, you'll learn about why regression models are used, the available types of regression models in machine learning, and the steps required to train a regression model. Next, you'll examine the best metrics for determining which regression model to use. You'll learn how to use a subset of data to train the regression model and run the training pipeline. Finally, you'll explore how to use an existing pipeline to create a new inference pipeline and create and deploy a predictive service. This course is one in a collection that prepares learners for the Designing and Implementing a Data Science Solution on Azure (DP-100) exam.

Machine learning classification models are used to predict the class or category that an item belongs to. For example, using patient characteristics such as age, weight, and BMI to predict if they are at risk for specific diseases. In this course, you'll learn about using classification models in the Azure Machine Learning Studio. You'll explore the available types of classification models and the steps required to train a classification model. Next, you'll learn the ideal metrics for determining the best classification model to use for the given data. Finally, you'll examine how to use an existing pipeline to create a new inference pipeline and create and deploy a predictive service for a classification 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.

Machine learning clustering models are used to group similar items based on their features and use unsupervised learning. In this course, you'll learn about using clustering models in the Azure Machine Learning Studio. First, you'll explore the available types of clustering models in Azure Machine Learning Studio and the steps required to train a clustering model. Next, you'll learn how to train and evaluate a clustering model. Next, you'll examine how to create a K-means clustering model in Azure Machine Learning Studio. Finally, you'll learn how to create and deploy a new inference pipeline to create a predictive service for a clustering 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.

Data scientists spend a majority of their time exploring and analyzing data, which may become the foundation for a machine learning model. The Azure Machine Learning Studio provides Jupyter Notebooks that can be used to perform data analysis. In this course, you'll learn about project Jupyter and how it is used for by data scientists to perform data analysis. You'll explore how to create a compute instance in Azure Machine Learning Studio and clone a sample training repository. Next, you'll learn how to use a Jupyter Notebook to perform basic data analysis and , create a regression model, classification model, and clustering model. Finally, you'll examine how to use Jupyter Notebook to perform deep learning using PyTorch and perform deep learning using TensorFlow. This course is one in a collection that prepares learners for the Designing and Implementing a Data Science Solution on Azure (DP-100) exam.

Azure Machine Learning workspaces provide an environment for performing experiments and managing data, computer targets, and other assets. Other assets can include notebooks, pipelines, and trained models. This course will focus on using the Azure Machine Learning SDK. In this course, you'll learn to create an Azure Machine Learning workspace by creating a machine learning resources, creating compute resources, and cloning a notebook. Next, you'll examine how to install the Machine Learning SDK for Python and create code to connect to a workspace. You'll learn to create Python scripts to run an experiment, log metrics, and retrieve and view logged metrics. Finally, you'll examine how to use the Azure Machine Learning SDK to run code experiments, create a script to train a model, and run a notebook using Jupyter to train predictive models. This course is one in a collection that prepares learners for the Designing and Implementing a Data Science Solution on Azure (DP-100) exam.