Top 20 NuGet machinelearning Packages

NumSharp is the fundamental library for scientific computing with .NET providing a similar API to python's numpy scientific library. NumSharp has full N-D, broadcasting and axis support. If you want to use .NET to get started with machine learning, NumSharp will be your best tool.
Amazon Machine Learning is a service that makes it easy for developers of all skill levels to use machine learning technology.
Google's TensorFlow full binding in .NET Standard. Docs: https://tensorflownet.readthedocs.io
Dlib wrapper library written in C++ and C# for Windows, MacOS and Linux Requirements: Visual C++ 2017 Redistributable Package
Dlib wrapper library written in C++ and C# for Windows, MacOS and Linux Requirements: Visual C++ 2017 Redistributable Package, cublas64_92.dll, cudnn64_7.dll, curand64_92.dll and cusolver64_92.dll
The world's simplest facial recognition api for .NET This library is ported from https://github.com/ageitgey/face_recognition by C#.
Provides learning algorithms and models for DecisionTree regression and classification.
Provides learning algorithms and models for RandomForest and ExtraTrees regression and classification.
Provides ensemble learning for regression and classification.
Provides learning algorithms and models for neural net regression and classification.
Provides learning algorithms and models for AdaBoost regression and classification.
Provides learning algorithms and models for GradientBoost regression and classification.
Provides optimization algorithms.
Provides classification, regression, impurity and ranking metrics.
Bright Wire is an open source machine learning library. Includes neural networks (feed forward, convolutional and recurrent), naive bayes, linear regression, decision trees, logistic regression, k-means clustering and dimensionality reduction.
Bright Wire CUDA adds GPU support to Bright Wire. This lets you run Bright Wire machine learning on a Maxwell or better NVIDIA GPU.
Provides learning algorithms and models for XGBoost regression and classification.
The world's simplest facial recognition api for .NET This library is ported from https://github.com/ageitgey/face_recognition by C#.
This is the .net standard 2 version of Bright Wire. Bright Wire is an open source machine learning library. Includes deep learning (feed forward, convolutional and recurrent), naive bayes, linear regression, decision trees, logistic regression, k-means clustering and dimensionality reduction.
This is the .net standard 2 version of BrightWire.CUDA which adds CUDA support to Bright Wire. This lets you run Bright Wire machine learning on a Maxwell or better NVIDIA GPU (x64 only).