MIARA dossier thématique

Generative Adversarial Networks

Item

Titre (article, livre complet, chapitre de livre, publication réseaux sociaux, pageWeb, SiteWeb complet, etc.)

Generative Adversarial Networks

Auteur de la référence bibliograpique

Ian J. Goodfellow

Jean Pouget-Abadie

Mehdi Mirza

Bing Xu

David Warde-Farley

Sherjil Ozair

Aaron Courville

Yoshua Bengio

Date de publication (AAAA ou AAAA-MM-JJ)

2014-06-10

URL (adresse Web)

http://arxiv.org/abs/1406.2661

is in semantic relation with

machine learning

machine learning

Is Referenced By

IFFHLKNN

Abstract

We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model D that estimates the probability that a sample came from the training data rather than G. The training procedure for G is to maximize the probability of D making a mistake. This framework corresponds to a minimax two-player game. In the space of arbitrary functions G and D, a unique solution exists, with G recovering the training data distribution and D equal to 1/2 everywhere. In the case where G and D are defined by multilayer perceptrons, the entire system can be trained with backpropagation. There is no need for any Markov chains or unrolled approximate inference networks during either training or generation of samples. Experiments demonstrate the potential of the framework through qualitative and quantitative evaluation of the generated samples.

is compiled by

ARCANES

gabarielleg

Source

arXiv.org

Date Submitted

2024-10-24T00:33:23Z

doi

10.48550/arXiv.1406.2661

Media

GAN_goodfellowSchema