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

ArtNet - IBM OpenPOWER Cognitive Cup Contest Wi...

ArtNet - IBM OpenPOWER Cognitive Cup Contest Winning talk

ArtNet - IBM OpenPOWER Cognitive Cup Contest Winning talk

Praveen Sridhar

November 15, 2016
Tweet

More Decks by Praveen Sridhar

Other Decks in Technology

Transcript

  1. What ArtNet Does ArtNet “knows” what a painting is about.

    Be it a landscape or still life or a portrait, or any of the different art genres. Examples of genres : Still Life Cityscape Religious
  2. Implementation ArtNet uses • a Convolution Neural Network to figure

    out patterns in a painting • and classifies it into different genres
  3. Implementation The OpenPOWER Deep Learning Distribution Frameworks like Theano and

    Tensorflow available as Pre-built binaries optimized for GPU acceleration Adding Keras was a breeze, since it runs on top of Theano or Tensorflow
  4. Hyperparameter Optimization The Real Deal Enter the “hyperas” library A

    very simple convenience wrapper around hyperopt for fast prototyping with keras models.
  5. Enter the “elephas” library Distributed Deep Learning with Keras &

    Spark Thought : SuperVessel Cloud makes it a breeze to spin up multi node spark instances, why not use it as Nitrox! ;)
  6. Going Forward • Predict the artist given a painting •

    Help Social Science people in understanding art influences : ✴ which artist influenced whom? ✴ to what extent?