22 packages returned for Tags:"networks"

The AForge.Neuro library contains classes for artificial neural network computation - feed forwards networks with error back propagation learning and Kohonen self organizing maps. Full list of features is available on the project's web site.

This is a lightweight package which is able to run neural networks with weights from different sources like Keras models.

Contains neural learning algorithms such as Levenberg-Marquardt, Parallel Resilient Backpropagation, initialization procedures such as Nguyen-Widrow and other neural network related methods. This package is part of the Accord.NET Framework.

Provides virtual network management capabilities for Microsoft Azure.

Catalyst is a Natural Language Processing library built from scratch for speed. Inspired by spaCy's design, it brings pre-trained models, out-of-the box support for training word and document embeddings, and flexible entity recognition models.

Use this Extension for HTTP Endpoints, HTTP Requests, Socket Endpoints, Socket Clients and SSDP discovery

A lightweight, linq-friendly inference library for .NET

Parallel Neural Network Classes for .NET. Backpropagation class for easy training and testing. Code Project link: http://www.codeproject.com/Articles/1016734/Parallel-Artificial-Neural-Networks-in-NET-Frame GitHub link: https://github.com/hemanthk119/NeuralNetworks/

Hype is a proof-of-concept deep learning library, where you can perform optimization on compositional machine learning systems of many components, even when such components themselves internally perform optimization. This is enabled by nested automatic differentiation (AD) giving you access to the... More information

A powerful neural network library for creating perceptron for classifying inputs. Also see SodiumPlusTraining for training neural networks using the error backpropagation approach.

uBeSocial is an Umbraco Back-Office extension that allows for easy posting to multiple social networks at once.

A library for quick implementation of neural networks

A library for serializing/deserializing neural networks created with SodiumPlus

A library for training neural networks created with SodiumPlus

Simple Library to expose network connections (TCP/UDP) per process, can be searchable by process id or process name. in first use the library must be initialize, the tables can be overwrited later.

A complete C# re-write of Berkeley's open source Convolutional Architecture for Fast Feature Encoding (CAFFE) for Windows C# Developers with full On-line Help, now with Single-Shot MultiBox, TripletNet, SiameseNet, NoisyNet, Deep Q-Network and Policy Gradient Reinforcement Learning, cuDNN LSTM... More information

The package helps to share any Umbraco document type in Linkedin, Twitter, and Facebook via one click. For now, you will never forget to share your blog post, news item or any other content on social networks. Please, carefully read quickstart tutorial to begin.

DyNet is a neural network library developed by Carnegie Mellon University and many others. It is written in C++ (with bindings in Python and C#) and is designed to be efficient when run on either CPU or GPU, and to work well with networks that have dynamic structures that change for every training... More information

Text Analytics and Sentiment Analysis API - allows to perform following: Sentiment analysis, Document classification, Entity extraction, Themes discovery, Keyword analysis, Citation detection, Slang detection..

Simple library for creating sequential models of convolutional neural networks. Library is for the solving small problems because is aimed on the readable code and modularity more than performance.