Richard Humphreys |
Microsoft has released its machine learning system Infer.NET on the open-source site GitHub. Developers can use the technology to add intelligence to the programs and apps they are building.
Infer.NET has already been used to try to understand and predict childhood asthma, leading to “the potential of significant clinical impact”. It has also helped to pair gamers playing Halo 5 and match film fans with movies they might like. It is also used in Microsoft services such as Office and Azure.
“Open-sourcing Infer.NET represents the culmination of a long and ambitious journey,” said Yordan Zaykov, principal research software engineer lead at Microsoft Research. “Our team at Microsoft Research embarked on developing the framework in 2004. We’ve learned a lot along the way about making machine learning solutions that are scalable and interpretable.
“Infer.NET was initially envisioned as a research tool and we released it for academic use in 2008. As a result, there have been hundreds of papers published using the framework across a variety of fields, from information retrieval to healthcare. In 2012 Infer.NET won a Patents for Humanity award for aiding research in epidemiology, genetic causes of disease, deforestation and asthma.
“The Infer.NET team is looking forward to engaging with the open-source community in developing and growing the framework further.”
Infer.NET can learn as new data is entered into it, which is useful for systems that are used by consumers, and it is also scalable – Microsoft researchers have used it to study information from billions of web pages.