At Build developer conference early this year, Microsoft announced ML.NET, a cross-platform machine learning framework that will enable .NET developers to develop their own models and infuse custom ML into their apps without any experience in working with machine learning models.
Recently, Microsoft announced the release of ML.NET 0.3 with support for exporting models to the ONNX format, support for creating new types of models with Factorization Machines, LightGBM, Ensembles, and LightLDA, and various bug fixes and issues reported by the community. Read about these new features and improvements using the links below.
- Export of ML.NET models to the ONNX-ML format
- Added LightGBM as a learner for binary classification, multiclass classification, and regression
- Added Field-Aware Factorization Machines (FFM) as a learner for binary classification
- Added Ensemble learners enabling multiple learners in one model
- Added LightLDA transform for topic modeling
- Added One-Versus-All (OVA) learner for multiclass classification