Live Coding A Machine Learning Model from Scratch (Google I/O’19)


48 Comments

  1. Junior studio

    May 8, 2019 at 7:11 pm

    Thanks

  2. Segoviano

    May 8, 2019 at 8:00 pm

    so… can i now build a ML model to stabilize this video?

  3. Jon Masters

    May 9, 2019 at 4:49 am

    Awesome video! This is my favorite from I/O 2019 by far!

  4. Sarthak Joshi

    May 9, 2019 at 8:12 am

    ML ML ML!

  5. Wojciech Duranowski

    May 9, 2019 at 3:34 pm

    very interesting and well-structured presentation

  6. MrTubber44

    May 9, 2019 at 5:59 pm

    I like Sara. Amazing content errytime!;-)

  7. Animesh Sharma

    May 9, 2019 at 7:22 pm

    from model building to deployment in less than an hour! and handling the live demo gotcha gracefully #awesome

  8. Al L

    May 10, 2019 at 2:18 am

    Very informative video. You explanation of how ML is doing matrix multiplication under the hood was amazing! As were your descriptions of one-hot and bag-of-words encoding. Never heard of SHAP before, looks like something I would find very useful. Thank you!

  9. Mohamed Ali

    May 10, 2019 at 6:06 am

    Good talk. Thank you.

  10. Machine Learning। মেশিন লার্নিং । হাতে কলমে

    May 10, 2019 at 8:44 am

    Great insight!

  11. Black Hazard

    May 10, 2019 at 2:48 pm

    What's that phython noetbook ??

  12. Cedric Villani

    May 11, 2019 at 2:16 am

    yes I have a suggestion, if your going to represent google and not even YOU can get a working live demo by the end, don't blame it on something fictional. It's a bad look, if the employees can't figure it out lol how are the rest of us mortals expected to.. Other then that was a nice quick overview, a verywell setup notebook demo page also.

  13. Akash Dhar

    May 11, 2019 at 9:12 am

    Why didn’t you use CountVectorizer from sklearn for tokenizing?

  14. Harshad Patil

    May 11, 2019 at 9:45 am

    Thanks Sara!! It was a very informative session!!

  15. Kenny Contreras

    May 11, 2019 at 12:07 pm

    Edit: I made a jupyter notebook with the code of this session: https://github.com/kennycontreras/Jupyter-Notebooks/blob/master/ML_model_Google_IO19.ipynb
    Amazing session! thanks for sharing! I'm an Anaconda Jupyter Notebook user and I liked a lot all the features of Colab. I'm going to give it a try.

  16. geekPanther

    May 11, 2019 at 12:11 pm

    Where can I Get the Code?

  17. shashank barki

    May 11, 2019 at 12:15 pm

    Thanks Sara and GCP ! This was an excellent presentation and demo.

  18. K7 Rockzzz

    May 11, 2019 at 1:53 pm

    ❤️

  19. Porus 91

    May 11, 2019 at 5:36 pm

    thanks for the demo…learned a lot……

  20. Krishna Mullapudi

    May 11, 2019 at 5:40 pm

    Awesome

  21. Narendra Prasath

    May 11, 2019 at 6:11 pm

    Very nice hands on coding. It would be better if you do it on regular basis on different kinds of problems.

  22. Pavan jadhav

    May 11, 2019 at 6:53 pm

    Nice elaboration!!

  23. mohammed ajmal

    May 11, 2019 at 7:56 pm

    😍

  24. username

    May 11, 2019 at 8:01 pm

    where is the colab file she used in the presentation?

  25. siddharth bhardwaj

    May 11, 2019 at 8:48 pm

    .

  26. Stephen Muga

    May 11, 2019 at 9:08 pm

    My model just outputs "Wakanda Forever" pls help

  27. Mastanpasha Shaik

    May 11, 2019 at 11:34 pm

    Good one!!

  28. Evans Kakpovi

    May 12, 2019 at 2:59 am

    Awesome video!!

  29. Evans Kakpovi

    May 12, 2019 at 3:00 am

    I can't wait to use tensor flow

  30. Junaid Akber

    May 12, 2019 at 6:50 am

    So helpful!

  31. Deno X

    May 12, 2019 at 12:27 pm

    This is inspiring, I have been doing it the hard way.

  32. Shaan

    May 12, 2019 at 4:10 pm

    This was class

  33. Shivani Garg

    May 12, 2019 at 5:22 pm

    It's great. Thanks

  34. VYOM RAJ

    May 12, 2019 at 11:38 pm

    Nicely explained!!

  35. Raihan Kabir Ratul

    May 13, 2019 at 9:47 am

    Can anyone help me with why am I getting different results in the 'code snippets' search option? eg. When I write "auth", "authenticate to your cloud account" option doesn't come.

  36. Subramaniam Iyer

    May 13, 2019 at 11:34 am

    The Matrix is real.

  37. Anand Baburajan

    May 13, 2019 at 1:04 pm

    Thank you!

  38. adhiyamaan pon

    May 13, 2019 at 1:33 pm

    amazing!!!

  39. Suhas Nama

    May 13, 2019 at 5:48 pm

    Awesome talk , thank you for the introduction to SHAP !!

  40. Lalit Jain

    May 14, 2019 at 6:52 pm

    This is amazing and almost instantly got me tuned in. Developed the code to reproduce here
    https://lalit7jain.wordpress.com/2019/05/14/deep-learning-classification-of-stackoverflow-questions-with-interpretability/

    Enjoy!

  41. Sara Robinson

    May 16, 2019 at 6:38 pm

    You can find the code from this demo here: https://github.com/GoogleCloudPlatform/ai-platform-text-classifier-shap

    And a blog post about it here: https://sararobinson.dev/2019/04/23/interpret-bag-of-words-models-shap.html

  42. Anoubhav Agarwaal

    June 13, 2019 at 4:53 pm

    Why don't use binary cross entropy and not categorical crossentropy ?

  43. mahdi fardi

    July 10, 2019 at 1:39 pm

    thanks so much 🙂

  44. zaphbeeblebrox

    July 29, 2019 at 10:34 pm

    Nicely done!! Thank you.

  45. Robo Cop

    December 7, 2019 at 3:05 pm

    Why didn't the last example work, did you figure it out?

  46. 袁智暉

    January 18, 2020 at 2:50 am

    very useful thank you

  47. vinoth uv

    February 25, 2020 at 7:20 pm

    Awesome Very useful thanks Sara

Leave a Reply