Articles, Blog Live Coding A Machine Learning Model from Scratch (Google I/O’19) Related posts: What’s New in Android Machine Learning (Google I/O’19) ML Kit: Machine Learning for Mobile with Firebase (Google I/O’19) Machine Learning Zero to Hero (Google I/O’19) From Systrace to Safetynet: Android Game Development Case Studies (Google I/O’19) build ml model cloud ai platform colab developer news developers google google 2019 Google I/O Google I/O 2019 Google IO google io updates google livestream I/O IO io 19 io announcements io19 live coding a ML model machine learning ML ML models tensor flow tensorflow Web Apps Post navigation Learning to backflip my MTBKnowing Brother ep 24 Han Chae-ah [ENG SUB] [SUB INDO] 48 Comments Mukesh May 8, 2019 at 6:47 pm Reply Cool Junior studio May 8, 2019 at 7:11 pm Reply Thanks Segoviano May 8, 2019 at 8:00 pm Reply so… can i now build a ML model to stabilize this video? Jon Masters May 9, 2019 at 4:49 am Reply Awesome video! This is my favorite from I/O 2019 by far! Sarthak Joshi May 9, 2019 at 8:12 am Reply ML ML ML! Wojciech Duranowski May 9, 2019 at 3:34 pm Reply very interesting and well-structured presentation MrTubber44 May 9, 2019 at 5:59 pm Reply I like Sara. Amazing content errytime!;-) Animesh Sharma May 9, 2019 at 7:22 pm Reply from model building to deployment in less than an hour! and handling the live demo gotcha gracefully #awesome Al L May 10, 2019 at 2:18 am Reply 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! Mohamed Ali May 10, 2019 at 6:06 am Reply Good talk. Thank you. Machine Learning। মেশিন লার্নিং । হাতে কলমে May 10, 2019 at 8:44 am Reply Great insight! Black Hazard May 10, 2019 at 2:48 pm Reply What's that phython noetbook ?? Cedric Villani May 11, 2019 at 2:16 am Reply 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. Akash Dhar May 11, 2019 at 9:12 am Reply Why didn’t you use CountVectorizer from sklearn for tokenizing? Harshad Patil May 11, 2019 at 9:45 am Reply Thanks Sara!! It was a very informative session!! Kenny Contreras May 11, 2019 at 12:07 pm Reply Edit: I made a jupyter notebook with the code of this session: https://github.com/kennycontreras/Jupyter-Notebooks/blob/master/ML_model_Google_IO19.ipynbAmazing 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. geekPanther May 11, 2019 at 12:11 pm Reply Where can I Get the Code? shashank barki May 11, 2019 at 12:15 pm Reply Thanks Sara and GCP ! This was an excellent presentation and demo. K7 Rockzzz May 11, 2019 at 1:53 pm Reply ❤️ Porus 91 May 11, 2019 at 5:36 pm Reply thanks for the demo…learned a lot…… Krishna Mullapudi May 11, 2019 at 5:40 pm Reply Awesome Narendra Prasath May 11, 2019 at 6:11 pm Reply Very nice hands on coding. It would be better if you do it on regular basis on different kinds of problems. Pavan jadhav May 11, 2019 at 6:53 pm Reply Nice elaboration!! mohammed ajmal May 11, 2019 at 7:56 pm Reply 😍 username May 11, 2019 at 8:01 pm Reply where is the colab file she used in the presentation? siddharth bhardwaj May 11, 2019 at 8:48 pm Reply . Stephen Muga May 11, 2019 at 9:08 pm Reply My model just outputs "Wakanda Forever" pls help Mastanpasha Shaik May 11, 2019 at 11:34 pm Reply Good one!! Evans Kakpovi May 12, 2019 at 2:59 am Reply Awesome video!! Evans Kakpovi May 12, 2019 at 3:00 am Reply I can't wait to use tensor flow Junaid Akber May 12, 2019 at 6:50 am Reply So helpful! Deno X May 12, 2019 at 12:27 pm Reply This is inspiring, I have been doing it the hard way. Shaan May 12, 2019 at 4:10 pm Reply This was class Shivani Garg May 12, 2019 at 5:22 pm Reply It's great. Thanks VYOM RAJ May 12, 2019 at 11:38 pm Reply Nicely explained!! Raihan Kabir Ratul May 13, 2019 at 9:47 am Reply 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. Subramaniam Iyer May 13, 2019 at 11:34 am Reply The Matrix is real. Anand Baburajan May 13, 2019 at 1:04 pm Reply Thank you! adhiyamaan pon May 13, 2019 at 1:33 pm Reply amazing!!! Suhas Nama May 13, 2019 at 5:48 pm Reply Awesome talk , thank you for the introduction to SHAP !! Lalit Jain May 14, 2019 at 6:52 pm Reply This is amazing and almost instantly got me tuned in. Developed the code to reproduce herehttps://lalit7jain.wordpress.com/2019/05/14/deep-learning-classification-of-stackoverflow-questions-with-interpretability/ Enjoy! Sara Robinson May 16, 2019 at 6:38 pm Reply 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 Anoubhav Agarwaal June 13, 2019 at 4:53 pm Reply Why don't use binary cross entropy and not categorical crossentropy ? mahdi fardi July 10, 2019 at 1:39 pm Reply thanks so much 🙂 zaphbeeblebrox July 29, 2019 at 10:34 pm Reply Nicely done!! Thank you. Robo Cop December 7, 2019 at 3:05 pm Reply Why didn't the last example work, did you figure it out? 袁智暉 January 18, 2020 at 2:50 am Reply very useful thank you vinoth uv February 25, 2020 at 7:20 pm Reply Awesome Very useful thanks Sara Leave a Reply Cancel Save my name, email, and website in this browser for the next time I comment.