Top 20 NuGet deep Packages

Microsoft Cognitive Toolkit Libraries, GPU Build
This is the Branch Xamarin SDK for Android, iOS and Forms applications.
What you have been waiting for. Perform a deep compare of any two .NET objects using reflection. Shows the differences between the two objects.
FastDeepCloner is very fast portable library, This is a C# cross platform library that is used to deep clone objects, whether they are serializable or not. It intends to be much faster than the normal binary serialization method of deep cloning objects.
Microsoft Cognitive Toolkit Libraries, CPU-Only Build
An extensible deep comparison library for .NET
Microsoft Cognitive Toolkit Libraries, UWP CPU-Only Build
Injects deep copy constructors and methods for properties.
Developing a C# wrapper to help developer easily create and train deep neural network models. Easy to use library, just focus on research Multiple backend - ArrayFire (In Progress), TensorSharp (In Progress), CNTK (Not Started), TensorFlow (Not Started), MxNet (Not Started) CUDA/ OpenCL support for...
Small Library for fast deep or shallow cloning .NET objects. It allows to copy everything and has a lot of performance tricks for fast copying.
CNTK CPU Only backend for SiaNet library. Please install SiaNet along with this backend.
ArrayFire backend for SiaNet library. Please install SiaNet along with this backend.
Contains Support Vector Machines, Decision Trees, Naive Bayesian models, K-means, Gaussian Mixture models and general algorithms such as Ransac, Cross-validation and Grid-Search for machine-learning applications. This package is part of the Accord.NET Framework.
Package Description
TensorFlow backend for SiaNet library. Please install SiaNet along with this backend.
MxNet backend for SiaNet library. Please install SiaNet along with this backend.
CNTK backend for SiaNet library. Please install SiaNet along with this backend.
Assert a result to an expected value and provide the diff
Provides learning algorithms and models for neural net regression and classification.
This is a lightweight package which is able to run neural networks with weights from different sources like Keras models.