/* ---- Google Analytics Code Below */

Thursday, June 22, 2017

Generative Adversarial Networks (GAN)

Similar in type to 'generate and test' methods.
GAN network   Generative adversarial network    Imitative.
      for creating new things that are like another.

 https://en.wikipedia.org/wiki/Generative_adversarial_networks

are a type of artificial intelligence algorithms used in unsupervised machine learning, implemented by a system of two neural networks competing against each other in a zero-sum game framework. They were first introduced by Ian Goodfellow et al. in 2014.[1]

This technique can generate photographs that look authentic to human observers.

 ..... One network is generative and one is discriminative.[1] Typically, the generative network is taught to map from a latent space to a particular data distribution of interest, and the discriminative network is simultaneously taught to discriminate between instances from the true data distribution and synthesized instances produced by the generator. The generative network's training objective is to increase the error rate of the discriminative network (i.e., "fool" the discriminator network by producing novel synthesized instances that appear to have come from the true data distribution). These models are used for computer vision tasks.[1][3]. ..... 

No comments: