addressalign-toparrow-leftarrow-rightbackbellblockcalendarcameraccwcheckchevron-downchevron-leftchevron-rightchevron-small-downchevron-small-leftchevron-small-rightchevron-small-upchevron-upcircle-with-checkcircle-with-crosscircle-with-pluscontroller-playcrossdots-three-verticaleditemptyheartexporteye-with-lineeyefacebookfolderfullheartglobegmailgooglegroupshelp-with-circleimageimagesinstagramFill 1light-bulblinklocation-pinm-swarmSearchmailmessagesminusmoremuplabelShape 3 + Rectangle 1ShapeoutlookpersonJoin Group on CardStartprice-ribbonprintShapeShapeShapeShapeImported LayersImported LayersImported Layersshieldstartickettrashtriangle-downtriangle-uptwitteruserwarningyahoo

6th Machine Learning Meetup

As you might have read in the popular press, Facebook is in the process of opening an engineering office here in London. I'm really happy to announce that the Facebook engineering team in London will be hosting us for our next meetup. Ralf Herbrich will be talking about a distributed real-time Bayesian learning platform built for online services.

I hope you'll be able to join us for a talk shortly after 18:00 and beer and pizza afterwards.

In Ralf's own words:

The last ten years have seen a tremendous growth in Internet-based online services such as search, advertising, gaming and social networking. Today, it is important to analyze large collections of user interaction data as a first step in building predictive models for these services as well as learn these models in real-time.

One of the biggest challenges in this setting is scale: not only does the sheer scale of data necessitate parallel processing but it also necessitates distributed models; with over 900 million active users at Facebook, any user-specific sets of features in a linear or non-linear model yields models of a size bigger than can be stored in a single system.

In this talk, I will give a hands-on introduction to one of the most versatile tools for handling large collections of data with distributed probabilistic models: the sum-product algorithm for approximate message passing in factor graphs. I will discuss the application of this algorithm for the specific case of generalized linear models and outline the challenges of both approximate and distributed message passing including an in-depth discussion of expectation propagation and Map-Reduce.

Join or login to comment.

  • Ralf H.

    Sorry for the delay - here is the video for those interested:

    1 · October 30, 2012

  • Ralf H.

    Thanks so much for everyone who was coming, the great interest in our work and the lively discussion! We took a video of the talk and for those who could not attend, we are planning to put the video live. I will keep you posted!

    October 17, 2012

    • Anish M.

      Look forward to the paper as well:)

      October 17, 2012

  • Richard B.

    Wouldn't let me in without signing an NDA which included terms I couldn't agree to (specifically, that all information learnt inside the building was private and not to be shared), so it wasn't a very good evening for me. A great shame.

    October 16, 2012

  • Christian P.

    Excellent talk.

    October 15, 2012

  • Karen

    Great people, great talk. Thanks!

    October 15, 2012

  • Wayne Z.

    It is such a great opportunity! So if possible, please add more space for those people on the waiting list.

    October 11, 2012

Our Sponsors

People in this
Meetup are also in:

Sign up

Meetup members, Log in

By clicking "Sign up" or "Sign up using Facebook", you confirm that you accept our Terms of Service & Privacy Policy