Generative Neural Nets

Generative Adversarial Networks (or GANs) have gained lot of popularity in recent years to generate new artificial data by feeding deep learning models with real data samples.. The model learns to create new samples by following the same distribution or patterns as in the real data-set used for training..

Applications of GANs in Media & Entertainment domain include:

  • Character Generation: Feed a GAN model with a sample of human-drawn characters like cartoons, caricatures, comic book action figures etc..
  • Automatic Scene Generation: Train GAN models on nature & landscape photography
  • Music Generation: Generate new soundtracks similar in style with music samples from specific genre, or composed by specific musician
  • Art Creation: Train GAN models on paintings, graphics & art illustrations