2 min Devops

Microsoft launches drag-and-drop machine learning tool

Microsoft launches drag-and-drop machine learning tool

Microsoft has announced three new services with the aim of simplifying the process of machine learning. It involves a new interface for a tool that fully automates the process of creating models, a new no-code visual interface for building, training and deploying models and hosting Jupyter-style notebooks.

The new tools make it easier to work with machine learning by hiding the code or giving those who want to write their own code a pre-configured platform to do so, TechCrunch writes.

The new interface for Azure’s automated machine learning tool should make it easier to create a model. Users import a dataset and tell the service what value to predict. No code needs to be written for this. The backside supports various new algorithms and optimizations that can result in more accurate models.

Although the service is fully automated, Microsoft says the service is “fully transparent about the algorithms so that developers and data scientists can overwrite and manage the process by hand”.

Azure Machine Learning

Microsoft has also unveiled a preview of a visual interface for its Azure Machine Learning service for users who want a little more control right away. This service allows users to build, train and deploy machine learning models without having to touch code.

The tool, the Azure Machine Learning visual interface, is quite similar to the existing Azure ML Studio. The new version should combine the best of that service with the Azure Machine Learning service. This means that the interface looks pretty much the same, but that it extends ML Studio’s capabilities by running on top of the Machine Learning service. The security, deployment and life cycle management capabilities of the service are added.

Finally, there are new hosted notebooks in Azure Machine Learning, which are more focused on more experienced machine learning developers. The notebooks come in a package that supports the Azure Machine Learning Python SDK and run in what the company describes as a “safe, enterprise-ready environment”. This feature allows developers to get started quickly, without having to set up a development environment with the required cloud resources first.

This news article was automatically translated from Dutch to give Techzine.eu a head start. All news articles after September 1, 2019 are written in native English and NOT translated. All our background stories are written in native English as well. For more information read our launch article.