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-circleimageimagesinstagramlinklocation-pinm-swarmSearchmailmessagesminusmoremuplabelShape 3 + Rectangle 1ShapeoutlookpersonJoin Group on CardStartprice-ribbonShapeShapeShapeShapeImported LayersImported LayersImported Layersshieldstartickettrashtriangle-downtriangle-uptwitteruserwarningyahoo

TensorFlow Meetup


The steaming link for the meetup: http://dai.ly/x4jzj7g

1. Project "Deep Water"- H2o's integration with Tensorflow by Jo-fai

http://bit.ly/h2o_paris_2_slides

This talk is about our recent project called "Deep Water". It is H2o's intergration with other deep learning libraries such as Tensorflow. I will go through the following topics: our motivation, potential benefits, H2o's interface and then a demo.

About Joe :https://uk.linkedin.com/in/jofaichow 

Jo-fai (or Joe) is a data scientist at H2O.ai. Before joining H2O, he was in the business intelligence team at Virgin Media where he developed data products to enable quick and smart business decisions. He also worked (part-time) for Domino Data Lab as a data science evangelist promoting products via blogging and giving talks at meetups. Joe has a background in water engineering. Before his data science journey, he was an EngD researcher at STREAM Industrial Doctorate Centre working on machine learning techniques for drainage design optimization. Prior to that, he was an asset management consultant specialized in data mining and constrained optimization for the utilities sector in UK and abroad. He also holds a MSc in Environmental Management and a BEng in Civil Engineering.

2. Cracking crack mechanics—Using GANs and TensorFlow to replicate and learn more about fracture patterns by Julien Launay

https://www.dropbox.com/s/itrlwk2wgtumjer/TensorFlow%20Meetup%20-%20CrackTools%20V2%20%28ANIM%29.compressed.pdf?dl=0

When modeling transfers through a medium in civil engineering, knowing the precise influence of cracks is often complicated, doubly so since the transfer and fracture problems are often heavily linked. I will present a new way to generate “fake” cracking patterns using GANs, and will then expand on how such novel techniques can be used to learn more about fracture mechanics. 

About Julien: https://fr.linkedin.com/in/julien-launay-400a7512a/en 

Julien Launay is a civil servant student at Cachan’s École Normale Supérieure. He is pursuing a MSc in Civil Engineering, with a personal focus on machine learning. His research project aims at building TensorFlow based tools to study cracking patterns in concrete. 


Join or login to comment.

  • marc m.

    Hello,
    Thank you for the slides.
    It looks like the talks are going to be cool :)
    From what I've read (in the slides) I believe we won't need our computers, can you confirm this ?
    Thank you ;)

    November 30

    • Jiqiong Q.

      No, you don't need your PC. But feel free to bring one if you want to test the demo en live. :)

      November 30

  • Bela B.

    J'abandonne ma place.

    November 30

  • Jo-fai C.

    Hi Everyone,

    My slides can be downloaded from this GitHub repo http://bit.ly/h2o_paris_2_slides

    See you soon.

    Cheers,
    Joe

    2 · November 30

    • touil

      Thank you chow

      November 30

  • Jiqiong Q.

    The slides for both talks are available. The steaming link will be published soon (thanks to dailymotion). Due to the limited capacity of the meeting room, make sure to arrive on time.
    Ji

    1 · November 30

  • Jo-fai C.

    I would love to give a talk in French one day ... unfortunately, this time it will be English :)

    2 · November 22

  • Tyler W.

    Are these meetups in French or English?

    1 · November 22

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