Upgrade to Pro — share decks privately, control downloads, hide ads and more …

The modern Python AI stack: an overview of TensorFlow

The modern Python AI stack: an overview of TensorFlow

Dražen Lučanin

April 20, 2017
Tweet

More Decks by Dražen Lučanin

Other Decks in Programming

Transcript

  1. 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”
  2. Getting into AI • …probably a good idea • Applying

    AI != researching AI • Modern AI frameworks – Torch (Facebook) – Theano (academy) – TensorFlow (Google)
  3. 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
  4. TF Overview • DataFlow programming language • describe a graph

    of interacting operations that run entirely outside Python – Graph – Session
  5. 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)
  6. Deployment • Google Cloud & AWS offer VMs with GPUs

    • FloydHub – Heroku for AI – https://www.floydhub.com/
  7. 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/