Machine learning (ML) is a field of artificial intelligence that uses statistical techniques to give computer systems the ability to “learn” (e.g., progressively improve performance on a specific task) from data, without being explicitly programmed.
Within the field of data analytics, machine learning is a method used to devise complex models and algorithms that lend themselves to prediction; in commercial use, this is known as predictive analytics. These analytical models allow researchers, data scientists, engineers, and analysts to “produce reliable, repeatable decisions and results” and uncover “hidden insights” through learning from historical relationships and trends in the data.
Most movie and music services and e-shops use machine learning to recommend similar products to their users, taking account their preferences. Azure Machine Learning studio is a browser based workbench for the data science workflow, which includes authoring, evaluating and publishing predictive models. In this tutorial we are going to see an overview of Azure Machine Learning studio and in the second part we are going to build a simple recommender.
You can access to Azure Machine Learning Studio either using a simple Microsoft Account. If you have an Azure Subscription you can also enable it from there. The different access options are listed here.
Create your account to access Azure Machine Learning Studio and lets get started.
Open Azure Machine Learning Service
Open Azure Machine Learning and login with your account. This is what you are going to see.
Click the upper-left menu and you’ll see several options.
Click Cortana Intelligence and you’ll be taken to the home page of the Cortana Intelligence Suite. The Cortana Intelligence Suite is a fully managed big data and advanced analytics suite to transform your data into intelligent action. See the Suite home page for full documentation, including customer stories.
Click Gallery and you’ll be taken to the Azure AI Gallery. The Gallery is a place where a community of data scientists and developers share solutions created using components of the Cortana Intelligence Suite.
Azure Machine Learning Studio
There are two options here, Home, the page where you started, and Studio.
Click Studio and you’ll be taken to the Azure Machine Learning Studio. First you’ll be asked to sign in using your Microsoft account, or your work or school account. Once signed in, you’ll see the following tabs on the left:
Projects are collections of experiments, datasets, notebooks, and other resources representing a single project. Their only purpose is to group resources. You can see all resources by clicking on your project name. By clicking the New button on the bottom you can create a new project.
Here you can find all the experiments that you have created and run or saved as drafts. Clicking on an experiment you can see a mini preview of it. By clicking the New button on the bottom you can create a new experiment.
By pressing the New button you can create a new blank experiment or choose an existing one from the Gallery. Once you are done you can also publish your experiment to the Gallery so it can be publicly available.
This is what an experiment looks like. On the right side you can see the menu and navigate to different options. In the right list you can see all the modules you can drag-and-drop into your experiment. In the main pane you will see your experiment workflow and on the right pane you can see the selected module properties.
Here you can see all the Web services that you have deployed from your experiments
Here you can find all the Jupyter notebooks that you have created.
All the Datasets that you have uploaded into Studio can be seen here. That includes Azure SQL Databases or files.
To create a new dataset click the New button. You can see all the different option you have of uploading new datasets, or updating an existing one.
Here you can find all the Models that you have trained in experiments and saved in ML Studio
Settings are a collection of settings that you can use to configure your account and resources.
This is a small overview of the options on Azure Machine Learning Studio environment. Now that you are ready you can begin building experiments. See the next part of the series Create a simple Movie recommender using Azure ML