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

A Short History of and Introduction to Deep Learning

For our March event, we are thrilled to have John Kaufhold from Deep Learning Analytics present a technical introduction to Deep Learning, one of the hottest topics in data science in the last couple of years. How hot? Go search for "deep learning", and skim through hundreds of hyperventilating news articles describing how it's used at Google, Facebook, Netflix, and more, and how it's beating image and speech recognition benchmarks at near-human levels of performance. At it's core, Deep Learning is in many ways just the next iteration of the venerable Artificial Neural Network, a repeatedly hyped machine learning technique almost as old as the digital computer. So what's real innovation, what's hype, how do Deep Learning nets actually work, what's new about them, and what does it matter to you, the data science practitioner? Join us and find out!

NOTE: We are extremely grateful to Arlington Economic Development, whose Arlington Meetup initiative helped us get access to an amazing venue for this event! We will be at the Artisphere, in Rosslyn. Plan to stick around for on-site Data Drinks afterwards!

6:30pm -- Networking, Food, and Refreshments

7:00pm -- Introduction

7:15pm -- Presentation and discussion

8:30pm -- Data Drinks (on-site cash bar!)

Abstract:

Big data and the emergence of data science as a formal discipline have both renewed interest in machine learning technologies that are scalable, fast, affordable and do not suffer from overfitting. Though the "No Free Lunch theorem" implies no machine learning technology in general can be expected to outperform all others on all tasks, some machine learning algorithms have been shown to consistently outperform others in empirical studies. For example, recent theoretical, algorithmic and practical breakthroughs in Deep Learning have been rapidly adopted and applied to industrial big data applications by the likes of Google, Apple and Facebook. Google+ image search and Siri, for example, both currently exploit Deep Learning algorithms developed in the past few years. In this talk I will discuss some recent Deep Learning history in the broader context of machine learning, highlighting the influence of Restricted Boltzman Machines, unsupervised feature learning, Dropout, rectified linear units, hierarchical distributed representations in deep architectures, GPU hardware acceleration, and open benchmarks."

Bio

Dr. Kaufhold is a data scientist and managing partner of Deep Learning Analytics, a data science company based in Arlington, VA. Prior to forming Deep Learning Analytics, Dr. Kaufhold investigated deep learning algorithms as a staff scientist at NIH. Prior to NIH, Dr. Kaufhold was a Technical Fellow at SAIC, serving as principal investigator or technical lead on a number of large government contracts funded by NIH, DARPA and IARPA, among others. Prior to joining SAIC, Dr. Kaufhold investigated machine learning algorithms for medical image analysis and image and video processing at GE's Global Research Center. Dr. Kaufhold earned his Ph.D. from Boston University's biomedical engineering department in 2001.

Sponsors:

This event is sponsored by Arlington Economic Development/Arlington Meetup, ClouderaStatistics.com, SynglyphXIBM Analytics Solution Center, and Elder Research. Would you like to sponsor too? Please get in touch!


Join or login to comment.

  • Ann V.

    FYI: "Deep Learning Startup Brings Cutting Edge Technology to Small Business":

    http://gigaom.com/2014/06/02/a-startup-called-skymind-launches-pushing-open-source-deep-learning/

    June 9, 2014

  • Majid A.

    you can try out this deep learning as a service http://www.ersatzlabs.com/services/

    1 · May 29, 2014

  • Jay K.

    Thanks everyone for coming out... Was a great time. Great questions, too. All that said, I received this last night on behalf of cats vicitmized by improved cat detection technology. NSA's PRISM program could have just included a budget for laser pointers.

    https://www.youtube.com/watch?v=ny_0zg3O_hY

    I hope the link works. Please let me know if it doesn't.

    1 · March 26, 2014

    • Doug_S

      Hilarious! Thank you!

      April 7, 2014

  • Harlan H.

    Mary Galvin wrote a blog review of this event, here: http://datacommunitydc.org/blog/2014/03/deep-learning-inspires-deep-thinking/ Check it out!

    April 1, 2014

  • Jim B.

    A deep presentation on a deep subject

    March 29, 2014

  • Jonathan H.

    Did someone say they had the audio from the meetup? [masked]

    March 29, 2014

  • Jerome Y.

    Learned a lot that was new to me. Stimulated me to learn more about deep learning.

    March 28, 2014

  • Mark Stephen L.

    great

    March 28, 2014

    • Christopher S.

      Thanks for the link Dave! Just downloaded but looks to be an awesome reference.

      March 24, 2014

    • Dave D.

      Also: Deep Learning Summer School: https://www.ipam.ucla....­ (including "A computational principle that explains sex, the brain, and sparse coding")

      3 · March 28, 2014

  • carlos r.

    Though it was very much the firehose, the lecture was very appropriate for those of us on the periphery of machine learning. Dr. Kaufhold placed the topic in historical context without requiring a lot of technical familiarity with the techniques. These are exciting times and we should be paying attention to developments in this field. Thank you, Dr. Kaufhold!

    March 27, 2014

  • Harlan H.

    Thanks to John for an amazing talk, and to everyone for coming and filling the venue to over capacity! John has OK'ed sharing his slides: https://drive.google.com/file/d/0B3aXKp9bt6OXQU5lU0lmOE1ZZjA/edit?usp=sharing Also, could the one or two people who expressed interest in blogging about this event get in touch, if still interested?

    2 · March 25, 2014

    • Ann V.

      thx so much! ... I was so sorry to have missed it - esp. after seeing all the great feedback reviews - so this is great!

      March 27, 2014

    • Miriam H.

      Thank you both, Harlan and Geoff. I was there and would love to have the opportunity to listen to it again.

      March 27, 2014

  • Scott S.

    Love this topic. Hinton had a great course on Coursera where he went into RBMs and Contrastive Divergence with some good exercises: https://www.coursera.org/course/neuralnets. Hopefully will be offered again.

    3 · March 24, 2014

    • A former member
      A former member

      Hopefully, but I'm not holding my breath. I've been keeping an eye on that course since I missed it the first time around, and I haven't heard a peep out of it. :/

      March 25, 2014

    • Sam L.

      Just wanted to point out: you can still watch all of the Coursera lectures, do the exercises, etc. It doesn't need to be current for you to access the content...

      March 26, 2014

  • A former member
    A former member

    Terrific talk! Well-prepared, appropriate for mixed technical audience, and fully cited.

    March 25, 2014

  • Nevin H.

    Outstanding! That Big Data stuff is getting mighty handy and sophisticated.

    March 25, 2014

  • Chris C.

    Excellent talk! A great introduction to deep learning woven together in a compelling story.

    March 25, 2014

  • Jeff G.

    Kudos to Data Science DC for this standing-room only event, and to John for an entertaining and fascinating talk. He made a very compelling case for exploring this growing technology.

    March 25, 2014

  • Majid A.

    ditto ditto ditto. ..and appreciated answering my questions.

    March 25, 2014

  • Saven

    Next time someone needs to video record John K's talk. I'm assuming he'll be invited back soon for another excellent presentation.

    March 25, 2014

  • Gregory P.

    We need a lab. We need to do some real deep learning.

    March 25, 2014

  • Tony F.

    Fascinating topic, wonderful speaker, great venue.

    Thanks to John and the DC Data Community team.

    March 25, 2014

  • Darron F.

    A thorough overview of DL given the time available. Thanks to DSDC and the sponsors for putting this event together for us.

    March 25, 2014

  • Kate y.

    Extremely organized talking with sharp comments. Thank you a lot.

    March 25, 2014

  • Matt P.

    A great talk. Well worth the time. Throughly enjoyed it.

    March 25, 2014

  • Bill K.

    Great and inspiring talk. Looking forward to the slides with the referenced papers.

    March 25, 2014

  • Gregory P.

    Got it the deck

    March 25, 2014

  • Gregory P.

    Where is the slide deck from this talk?

    March 25, 2014

  • Jay K.

    This talk was excellent!

    March 25, 2014

  • Gregory P.

    the best

    March 25, 2014

  • Jay K.

    To whoever asked the insightful question about the connection between quantum computing and machine learning, I'm not qualified to answer, but perhaps this interview with Geordie Rose (of DWAVE) will shed some light -johnk- http://m.youtube.com/watch?v=SuukrcJuHXw

    1 · March 25, 2014

  • Miriam H.

    An exception talk by an exceptional speaker. John Kaufhold miraculously wove concepts with theory with practical examples and then sprinkled the mixture with humor. His organizational style - pursuing modules/topics just enough to tease my attention span - was excellent and, when combined with a quick summary of the module, made for a tremendous learning experience. For me, the talk was at a perfect level. I had sufficient exposure to about 70+% of the material and the rest was presented in a thoroughly approachable manner. Kaufhold left me wanting more so that I will go do some research. Thank you organizers for this treat of a talk.

    1 · March 25, 2014

  • A former member
    A former member

    Phenomenal speaker, and he did a great job organizing and presenting the subject matter. (The topic was extremely interesting, too, of course.)

    1 · March 25, 2014

  • Peter W.

    This was a great talk!

    March 25, 2014

  • Siddharth P.

    Excellent

    March 25, 2014

  • Alex P.

    Using the resources provided in the talk, how practical is it really to implement a deep neural network?

    March 24, 2014

    • Majid A.

      the algorithms are already implemented in some codes if you just want to use them but it's wise to try and implement a few yourself to see how they work. see the ref.s.

      1 · March 24, 2014

  • A former member
    A former member

    Good, technical talk by a very entertaining speaker! Great talk!!

    1 · March 24, 2014

  • Evelyn

    The topic of Deep Learning & technical methodology is a bit over my head. But overall the approach is comprehensive. The speaker is very knowledgable.

    March 24, 2014

  • David B.

    Amazing talk! Please tell me was there a video?

    March 24, 2014

  • Assaf S.

    Good talk; very effective speaker

    March 24, 2014

  • Greg T.

    50.3% of the people here tonight have worked with Neural Nets

    1 · March 24, 2014

  • Ryan B. H.

    Here at Artisphere. Where to?

    March 24, 2014

  • Gallagher P.

    Who, if anyone, is sponsoring?

    March 13, 2014

    • Harlan H.

      Please see the sponsor list in the event listing and web site sidebar. (It's been updated a couple times since the event's been posted, so I won't re-post the list here and risk this comment going out of date.) Thanks to those sponsors for making this event happen!

      March 14, 2014

  • Harlan H.

    We'd love your help getting the word out about this event! Please print a copy of the flier ( http://files.meetup.com/2215331/DSDC%20Mar%202014.pdf ) and post it on cork boards, on your office door, near the elevator, etc. Thanks!

    March 5, 2014

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