The modern Python AI stack: an overview of TensorFlow Dražen Lučanin 

AI: The Next Big Thing™ ● Communication was the Internet’s killer app – web apps storing data to DBs ruled ● My view… AI will be the next killer app – Faster & cheaper GPU hardware – Lots of R&D around machine learning – Cool applications ● Self-driving cars ● Good speech recognition ● Automating repetitive manual tasks ● “The secret sauce” 

Getting into AI ● …probably a good idea ● Applying AI != researching AI ● Modern AI frameworks – Torch (Facebook) – Theano (academy) – TensorFlow (Google) 

TensorFlow (TF) ● Great AI framework built in Google – Easy for developers and researchers – Production-ready ● MapReduce – White paper only – Hadoop became the standard ● TF open sourced to became the standard ● Model marketplace 

TF Overview ● DataFlow programming language ● describe a graph of interacting operations that run entirely outside Python – Graph – Session 

TF API ● Low-level API (for researchers) ● High-level API (GTD) ● Example 

Performance ● CPU (C++ implementation – pretty efficient) ● GPU – even faster! ● JIT compiler – Speed things up by adding a single line of code – Experimental ● XLA compiler – Ahead-of time compilation – Run on embedded devices (phones, IoT) 

TensorBoard 

Deployment ● Google Cloud & AWS offer VMs with GPUs ● FloydHub – Heroku for AI – https://www.floydhub.com/ 

Learning ● Easy riding – https://changelog.com/podcast/219 – TF Dev Summit ‘17 videos – https://events.withgoogle.com/tensorflow-dev-summit/ ● Docs & tutorial – https://www.tensorflow.org/get_started/get_started – https://medium.freecodecamp.com/big-picture-machine-learning-classifying-text- with-neural-networks-and-tensorflow-d94036ac2274 ● Goood free books – ESL – http://statweb.stanford.edu/~tibs/ElemStatLearn/ – Michael Nielsen – http://neuralnetworksanddeeplearning.com/ ● Research – http://distill.pub/ 

Thanks! ● Dražen Lučanin ● @metakermit ● Building apps with a kick! https://punkrockdev.com/