Articles, Blog TensorFlow and Deep Learning without a PhD, Part 2 (Google Cloud Next ’17) Related posts: TensorFlow and Deep Learning without a PhD, Part 1 (Google Cloud Next ’17) How to Do Sentiment Analysis – Intro to Deep Learning #3 How Machine Learning is Impacting Oil and Gas (Cloud Next ’18) What is a Deep Learning Library? – Ep. 16 (Deep Learning SIMPLIFIED) #GoogleNext17 beginners cloud Cloud NEXT Convolutional Networks deep learning dense networks Developer GCP google cloud Language language model machine learning Networks neural networks recurrent neural networks Technical technical video tensorflow Post navigation Theory of Knowledge: Human Sciences, Dr Marianna KoliMIT 6.S094: Deep Reinforcement Learning for Motion Planning 18 Comments Q World March 28, 2017 at 8:03 pm Reply Thanks a ton, very informative session! Eric Graf April 11, 2017 at 6:52 pm Reply Here is the Link to his github code https://github.com/martin-gorner/tensorflow-mnist-tutorial Hans Baier April 22, 2017 at 12:16 pm Reply Excellent tutorial. Thanks for sharing! Rowan Gontier April 29, 2017 at 10:26 am Reply Wonderful stuff. 大老表 May 4, 2017 at 6:16 pm Reply I feel too small, too much things to learn…… August Karlstedt June 8, 2017 at 6:03 am Reply Too bad; still getting a PhD 😂 Ivan Cavattoni June 29, 2017 at 5:55 pm Reply Why CELLSIZE is 512? Is there some reason you choose 512? kunwar singh July 21, 2017 at 8:19 pm Reply good work Martin Gaurav Singh July 22, 2017 at 6:20 am Reply After going through so many YouTube videos on Tensorflow, I stumble upon this amazing multi part video series and wow… each concept is explained so clearly in such a precise manner… Thanks a lot Martin!!Really looking forward to more such Amazing videos from you Darkarix August 6, 2017 at 9:53 pm Reply What is the advantage of having a 3 layer network? if the minibatch sequencer has to follow the sentence it practically treats one layer at a time I don't understand how it is improving the training to have them connected, is it just to save computation power or there's more to it?? Mona Chu September 2, 2017 at 3:32 pm Reply If High School math, a simple linear equation can do such magic in TensorFlow, just think what would the mathematical knowledge of a Mathematician, Physicist, or an engineer would do for AI. Knowing Quantum computer is now in used, I am so excited and scared, just as scientists first heard an atomic bomb had been detonated. Ayman Shams September 28, 2017 at 10:42 am Reply Is there a lab available for RNN? Fairuz Shadmani Shishir October 6, 2017 at 5:19 am Reply very helpful Andrew January 12, 2018 at 10:16 pm Reply Cool scarf bro Рудольф Зайдель January 25, 2018 at 11:30 pm Reply Where is part 3? Or where I can find next? Tnx Wang Zhe May 13, 2018 at 9:38 am Reply refer to 3:24, isn't it suppose to be softmax, but the computed probabilities doesn't sum up to 1 in your slide. Siddharth Kotwal July 28, 2018 at 3:57 pm Reply Great tutorial, love the first principles thinking. I think this is the first time I've understood how the TF developers were thinking while writing these abstractions for RNNs. Martin Görner August 21, 2018 at 6:19 pm Reply The code for all the "Tensorflow without a PhD" sessions is now in a single place on GitHub: https://github.com/GoogleCloudPlatform/tensorflow-without-a-phdThe series now has 6 sessions. You will find the videos and slide decks at the URL above as well. Leave a Reply Cancel Save my name, email, and website in this browser for the next time I comment.