Difference between revisions of "Generative AI"

From
Jump to: navigation, search
Line 31: Line 31:
 
*** [[Semi-Supervised Learning with Generative Adversarial Network (SSL-GAN)]]
 
*** [[Semi-Supervised Learning with Generative Adversarial Network (SSL-GAN)]]
 
*** [[Context-Conditional Generative Adversarial Network (CC-GAN)]]
 
*** [[Context-Conditional Generative Adversarial Network (CC-GAN)]]
 +
  
 
<i>[http://developers.google.com/machine-learning/gan/generative Background: What is a Generative Model? | Google]</i>
 
<i>[http://developers.google.com/machine-learning/gan/generative Background: What is a Generative Model? | Google]</i>
Line 45: Line 46:
 
* <b>Generative</b> models can generate new data instances.
 
* <b>Generative</b> models can generate new data instances.
 
* <b>Discriminative</b> models discriminate between different kinds of data instances.
 
* <b>Discriminative</b> models discriminate between different kinds of data instances.
 +
  
  

Revision as of 19:56, 2 October 2019

YouTube search... ...Google search



Background: What is a Generative Model? | Google

More formally, given a set of data instances X and a set of labels Y:

  • Generative models capture the joint probability p(X, Y), or just p(X) if there are no labels.
  • Discriminative models capture the conditional probability p(Y | X).

A generative model includes the distribution of the data itself, and tells you how likely a given example is. For example, models that predict the next word in a sequence are typically generative models (usually much simpler than GANs) because they can assign a probability to a sequence of words.

Informally:

  • Generative models can generate new data instances.
  • Discriminative models discriminate between different kinds of data instances.



Deep Generative Modeling


Agents


Generative Modeling Language