ML .NET is the new framework which is developed by the Microsoft and released May 6th,2019 for .Net ecosystem. It allows developers to create custom ML models using C# or F# without having to leave the .NET ecosystem. It is an open source and cross-platform machine learning framework which is designed as an extensible platform to consume other popular ML frameworks like Tensor-Flow, ONNX, Infer.NET, and more).
ML .NET also brings a simple UI tool which is called "Model Builder" and CLI to make easier to build custom ML Models, at the same time.
ML.NET framework used by many Microsoft products such as Windows Defender, Microsoft Office ( Powerpoint design ideas, Excel Chart recommendations), Azure Machine Learning! Also it is being used by many organizations like SigParser (Spam Email Detection), William Mullens (Legal Issue Classification) and Evolution Software (Moisture Level Detection for Hazelnuts).
Getting started with any subject to learn involves a steep learning curve, it is the same for machine learning too. First is first, to be able to build custom machine learning models, you have to figure out which machine learning type to pick for your scenario, it can be classification or regression? Then you need to transform your data into a format that ML algorithms can understand (from textual data to numeric vectors). If you are just a new to ML, those steps can be pretty daunting!
Automated Machine is designed to make your machine learning journey easier by automatically figuring out how to transform your input data and determining the best performing Machine Learning Algorithm to help you to build best class custom, ML models. Automated ML supports both Regression and Classification machine learning tasks.
Data Representation
Data-types such as IDataView
Machine Learning Tasks
Binary Classification
Multi-Class classification
Regression
Ranking
Anomaly Detection
Clustering
Recommendation (preview)
Data Transformation and featurization
Text
Categories
Feature Selection
Normalization and missing value handling
Image featurization
Time Series (preview)
Support for ONNX and Tensor-Flow model integration (preview)
Sentiment Analysis
Customer Segmentation
Product Recommendation
Object Detection
Image Classification
Price Prediction
Fraud Detection
Sales Forecasting
Having such a framework in the .NET ecosystem is very impressive, and I am pretty sure that it will be very helpful for the developers who want to use machine learning in the projects, specifically considering "cross-platform support" of this framework and extensibility with Tensor-Flow, ONNX, Infer.NET, and more, will be the striker feature of this framework.
You can continue with the tutorial series that I shared which are about using Microsoft ML.Net with various examples from the real-life scenarios. I believe that this serial will be handy for developers who want to exist in the new generation of software development.