# Difference between revisions of "stat946w18/IMPROVING GANS USING OPTIMAL TRANSPORT"

From statwiki

(Created page with "== Introduction ==") |
(→Introduction) |
||

Line 1: | Line 1: | ||

== Introduction == | == Introduction == | ||

+ | Generative Adversarial Networks (GANs) are powerful generative models. It consists of a generator and a discriminator or critic. The generator is a neural network which learns to generate data as similar to the real distribution as possible. The critic measures the distance between the generated data distribution and the real data distribution which uses to distinguish between the generated data and training data. | ||

+ | |||

+ | Optimal transport theory is a similar approach to measure the distance between the generated data and training data distribution. |

## Revision as of 15:54, 12 March 2018

## Introduction

Generative Adversarial Networks (GANs) are powerful generative models. It consists of a generator and a discriminator or critic. The generator is a neural network which learns to generate data as similar to the real distribution as possible. The critic measures the distance between the generated data distribution and the real data distribution which uses to distinguish between the generated data and training data.

Optimal transport theory is a similar approach to measure the distance between the generated data and training data distribution.