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

Deep learning demos + roundtable discussion

Hi neural netters,

Last time we met was back in June.  Since then, there have been a handful of developments in deep learning--this includes research into different types of nonlinearities (max out, "p-norm"), using autoencoders as generative models, and some very nifty research related to NLP and how learned word vectors can be linearly combined for interesting results--eg. vector('queen')+vector('chair') ~= vector('throne').  There's a lot of work going into *applications* of deep learning now.

Meanwhile, my company has also been heads down working on Ersatz, our deep learning PaaS.  It's got a long way to go, but I'm comfortable saying it's currently the most powerful and easy to use set of deep learning tools available.  Then again, it's not yet a crowded market (wait till this time next year...)

So let's have a meetup.  Last time, I did a demo for the first half and had sort of a free wheeling roundtable discussion during the second half.  I think the roundtable worked particularly well, so let's do that again.  I'll make sure to get it on tape this time :-)

So agenda:

Since dreamforce (big salesforce.com convention) is in town, I'll be demoing an actual real life use case for using neural networks (in this case, the networks implemented in Ersatz) to plan a day's calls for a busy salesperson automatically--IE, answer the question "Statistically, what are the most beneficial actions I can take today in order to improve my odds of hitting my sales target?"  

I'll also show a much more "fun" demo where I take a bunch of learned word vectors and map them into a 3 dimensional space using T-SNE and render something like 300,000 unique words into a 3d space using three.js w/ webGL.

Then we'll just discuss whatever you want re: machine learning, deep learning, neural networks, moving towards AI, how it all ties together, etc. etc.

Booze will be provided as per usual.  Because if there's anything that goes with hardcore optimization of graphical models, it's booze...

Re: group in general:

Lately (like, last 6 months), I haven't had enough time to host these as often as I'd like.  SO if anyone would like to step up and help out with hosting the one after this (which will probably be NIPS 2013 themed), I'd be ecstatic!  So anyway, let me know if you'd be up for planning one of these.

Thanks everyone, hope to see you there!

Join or login to comment.

  • Dave S.

    Thanks for coming everyone! I've spliced together the videos and put them on youtube, so if you didn't have a chance to make the event or you want to see it again, here it is: https://www.youtube.com/watch?v=1_M6XXUoG9w

    Thanks again and I hope to see you all at the next one which will probably be a review of interesting findings at NIPS 2013 (which is in early December)

    November 22, 2013

  • Niels J.

    Jeff Dean from Google spoke at Berkeley's AMPLab this afternoon on "Scaling Deep Learning". He was asked whether CPUs or GPUs are better for deep neural nets. His response: "GPUs are much better". He said they were findamentally better suited to the problem (lots of parallel computations with lots of communication with neighbors). The only reason they initially used CPUs was that they had lots of idle CPUs already available.

    1 · November 20, 2013

  • Eron W.

    Great event, thanks Dave!

    The word2vec code that was discussed:
    http://radimrehurek.com/2013/09/deep-learning-with-word2vec-and-gensim/

    A fun sample app of word2vec:
    http://www.thisplusthat.me/

    The Numenta code that was mentioned:
    https://github.com/numenta/nupic

    1 · November 19, 2013

  • Berkeley M.

    Learned a lot!

    November 18, 2013

  • Nagarajan D

    Freeing a slot..will not be able to make it before 7:30 as I missed train

    November 18, 2013

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