Search
Wednesday 12 December 2018
  • :
  • :

Machine Learning the Microsoft Way with ML.NET

Machine Learning the Microsoft Way with ML.NET

As more applications are being built with Artificial Intelligence in mind for a current or future need, there is more need to integrate Machine Learning early.

What is: Machine Learning made for .NET

ML.NET is an open source machine learning framework, created by Microsoft, for the .NET developer platform. ML.NET is cross platform and runs on macOS, Linux and Windows.

Use your .NET and C# or F# skills to easily integrate custom machine learning into your applications without any prior expertise in developing or tuning machine learning models.

Learn more about ML.NET

 

Libraries, and More Libraries.. Soon

ML.NET contains machine learning libraries created by Microsoft Research and used by Microsoft products. Over time, you will also be able to leverage other popular libraries like Accord.NET, CNTK and TensorFlow through the extensible platform.

How to get this technology to work for you?  

What Data Can you Load?

ML.NET can load the following types of data into your pipeline:

  • Text (CSV/TSV)
  • Parquet
  • Binary
  • IEnumerable<Τ>
  • File sets

Data in the Format You Need

Use the built-in set of transforms to get your data into the format and types that you need for processing. ML.NET offers support for:

  • Text transforms
  • Changing data schema
  • Handling missing data values
  • Categorical variable encoding
  • Normalization
  • Selecting relevant training features
  • NGram featurization

Choose Algorithm to Meet your Needs

Choose the learning algorithm that will provide the highest accuracy for your scenario. ML.NET offers the following types of learners:

  • Linear (e.g. SymSGD, SDCA)
  • Boosted Trees (e.g. FastTree, LightGBM)
  • K-Means
  • SVM
  • Averaged Perceptron

Many Models to Choose

Train ModelTraining your model by calling the LearningPipeline.Train method. The method will then return a PredictionModel object that uses your input and output types to make predictions.
Evaluate Model: ML.NET offers evaluators that will assess the performance of your model on a variety of metrics.
Deploy Model: ML.NET allows you to save your trained model as a binary file that you can integrate into any .NET application.

 

If you are interested in integrating Machine Learning into your applications.. partner with a Microsoft Gold Partner in Application Development  

 

To learn more and how you can get started:

ML.NET Tutorial – Get started in 10 minutes

GitHub’s ML.NET group

A Look at the New ML.NET API

Getting Started With Machine Learning .NET (ML.NET)

Microsoft smartens up the ML.Net machine learning API

Article about the Pros and Cons:  

.Net Developers can Write Machine Learning Code Too: The Case for and Against ML.NET

 

 

 

 

 

 

 

 




Leave a Reply

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.