开源.NET神经网络库？
声明：本页面是StackOverFlow热门问题的中英对照翻译，遵循CC BY-SA 4.0协议，如果您需要使用它，必须同样遵循CC BY-SA许可，注明原文地址和作者信息，同时你必须将它归于原作者（不是我）：StackOverFlow
原文地址: http://stackoverflow.com/questions/1549811/
Warning: these are provided under cc-by-sa 4.0 license. You are free to use/share it, But you must attribute it to the original authors (not me):
StackOverFlow
Open-source .NET neural network library?
提问by Chris
Can anyone recommend a good open-source .NET neural network library?
谁能推荐一个好的开源 .NET 神经网络库？
Thanks!
谢谢！
采纳答案by AndreyAkinshin
Best .NET neural network library is AForge
最好的 .NET 神经网络库是 AForge
Links:
链接：
回答by JeffHeaton
Encog is a free open source neural network API for both Java and DotNet.
Encog 是适用于 Java 和 DotNet 的免费开源神经网络 API。
回答by Daniel
In case this helps anybody else, MS SQL has pretty robust built-in Neural Network supportas part of Data Mining Analysis Services.
万一这对其他人有帮助，MS SQL 具有非常强大的内置神经网络支持，作为数据挖掘分析服务的一部分。
I know MS SQL isn't open source, but odds are if you are using .NET your data may already be in SQL.
我知道 MS SQL 不是开源的，但很可能如果您使用 .NET，您的数据可能已经在 SQL 中。
回答by mjv
NeuronDotNetIt is not as broad in its scope as AForge, but its exclusive focus on NN makes it maybe more readily accessible, and possibly more featured in this area.
NeuronDotNet它的范围不像 AForge 那样广泛，但它对 NN 的独家关注使它可能更容易访问，并且可能在该领域更有特色。
Update: (December 2012)
NeuronDotNet's old repository at http://neurondotnet.freehostia.comis defunct.
The most recent source code, Version 3.0is available on sourceforge, but this project is effectively inactive. Apparently, its original developer, and sole contributor, Vijeth Dinesha, has stopped updating and improving this code base. Thank you, Vijeth! Maybe someone will, some day, pick-up from where you left. Indeed, NeuronDotNet is a relatively mature framework and its simplicity and single focus make it attractive, compared with other frameworks where Neural Nets are just one feature/module therein.
更新：（2012 年 12 月）
NeuronDotNet 位于http://neurondotnet.freehostia.com的旧存储库已不复存在。sourceforge 上提供了
最新的源代码3.0 版，但该项目实际上处于非活动状态。显然，它的原始开发人员和唯一贡献者 Vijeth Dinesha 已停止更新和改进此代码库。谢谢你，维杰斯！也许有一天有人会从你离开的地方接你。事实上，NeuronDotNet 是一个相对成熟的框架，与神经网络只是其中一个功能/模块的其他框架相比，它的简单性和单一焦点使其具有吸引力。
回答by Norman H
Here is a list of F# related resources for open source .NET machine learning.
这是用于开源 .NET 机器学习的 F# 相关资源列表。
http://fsharp.org/machine-learning/
http://fsharp.org/machine-learning/
Frameworks available on NuGet: (The content below was taken directly from the above referenced URL for persistence purposes.)
NuGet 上可用的框架：（出于持久性目的，以下内容直接取自上述引用的 URL。）
Accord.MachineLearning - 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.
Encog Machine Learning Framework - An advanced neural network and machine learning framework. Encog contains classes to create a wide variety of networks, as well as support classes to normalize and process data for these neural networks. Encog trains using multithreaded resilient propagation. Encog can also make use of a GPU to further speed processing time. A GUI based workbench is also provided to help model and train neural networks.
Numl - A machine learning library intended to ease the use of using standard modeling techniques for both prediction and clustering
Accord.MachineLearning - 包含支持向量机、决策树、朴素贝叶斯模型、K 均值、高斯混合模型和通用算法，如机器学习应用程序的 Ransac、交叉验证和网格搜索。这个包是 Accord.NET Framework 的一部分。
Encog 机器学习框架 - 高级神经网络和机器学习框架。Encog 包含用于创建各种网络的类，以及用于规范化和处理这些神经网络数据的类。Encog 使用多线程弹性传播进行训练。Encog 还可以利用 GPU 来进一步加快处理时间。还提供了一个基于 GUI 的工作台来帮助建模和训练神经网络。
Numl - 旨在简化使用标准建模技术进行预测和聚类的机器学习库
回答by lmsasu
Download Wekaand convert from the jar file (Java bytecode) to .NET Framework (managed) dll through IKVM. Weka is aknowledged by many as a very good open-source library for machine learning. It includes neural networks.
下载Weka并通过IKVM将 jar 文件（Java 字节码）转换为 .NET Framework（托管）dll 。Weka 被许多人认为是一个非常好的机器学习开源库。它包括神经网络。
回答by Anatoli Klamer
https://dotnet.github.io/infer/Infer.NET is a framework for running Bayesian inference in graphical models.
https://dotnet.github.io/infer/Infer.NET 是一个在图形模型中运行贝叶斯推理的框架。
