Reverend Bayes, meet Countess Lovelace: Probabilistic Programming for Machine Learning

Download this episode

Download Video


We propose a marriage of probabilistic functional programming with Bayesian reasoning.  Infer.NET Fun turns the simple succinct syntax of F# into an executable modeling language – you can code up the conditional probability distributions of Bayes' rule using F# array comprehensions with constraints. Write your model in F#. Run it directly to synthesize test datasets and to debug models. Or compile it with Infer.NET for efficient statistical inference.  Hence, efficient algorithms for a range of regression, classification, and specialist learning tasks derive by probabilistic functional programming.







Available formats for this video:

Actual format may change based on video formats available and browser capability.

    The Discussion

    • User profile image

      Hi, you can download the zipfile with the machine learning software I'll talk about, here:

      Cheers, Andy

    • User profile image
      Francois Rouaix

      No doubt that Infer.NET and Infer.NET Fun are great tools, but they are currently distributed under a very restrictive license. Andy mentions Kaggle competitions, but many of them do require that all software used are unencumbered (either OSS or commercially available software). Even the fact that competitions have rewards may be a violation of the Infer.NET license.

    • User profile image
      Rick Minerich

      Please, please, please release this with a commercially usable license! It would make .NET a viable platform for machine learning.

    • User profile image
      Jack Fox

      +1 for a commercial Infer.NET license.

    Comments closed

    Comments have been closed since this content was published more than 30 days ago, but if you'd like to send us feedback you can Contact Us.