Infer.NET

Infer.NET is a free and open source .NET software library for machine learning.^[2] It supports running Bayesian inference in graphical models and can also be used for probabilistic programming.

Overview[]

Infer.NET follows a model-based approach and is used to solve different kinds of machine learning problems including standard problems like classification, recommendation or clustering, customized solutions and domain-specific problems. The framework is used in various different domains such as bioinformatics, epidemiology, computer vision, and information retrieval.^[3][4]

Development of the framework was started by a team at Microsoft’s research centre in Cambridge, UK in 2004. It was first released for academic use in 2008 and later open sourced in 2018.^[4] In 2013, Microsoft was awarded the USPTO’s Patents for Humanity Award in Information Technology category for Infer.NET and the work in advanced machine learning techniques.^[5][6]

Infer.NET is used internally at Microsoft as the machine learning engine in some of their products such as Office, Azure, and Xbox.^[7]

The source code is licensed under MIT License and available on GitHub.^[8] It is also available as NuGet package.^[9]

See also[]

• Machine learning
• ML.NET
• scikit-learn

References[]

Further reading[]

• Knowles, D.; Parts, L.; Glass, D.; Winn, John (2010). "Modeling skin and ageing phenotypes using latent variable models in Infer.NET" (PDF). Cite journal requires |journal= (help)
• Winn, John; Minka, Tom (2009). "Probabilistic Programming with Infer.NET". Cite journal requires |journal= (help)
• Winn, John; Simpson, Angela; Custovic, Adnan; Y. F. Tan, Vincent (2008). "Immune System Modeling with Infer.NET" (PDF). Cite journal requires |journal= (help)

External links[]

• Infer.NET
• GitHub - dotnet/infer
• Machine Intelligence and Perception - Microsoft Research
• Infer.NET - Practical Implementation Issues and a Comparison of Approximation Techniques