Generative adversarial nets

Item

Title
Generative adversarial nets
Advances in neural information processing systems
Is Referenced By
PKZXEY5K
Abstract
We propose a new framework for estimating generative models via adversarial nets, 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 quantitatively evaluation of the generated samples.
pages
2672-2680
Date
2014
Date Submitted
2021-06-11T12:38:09Z
is compiled by
ARCANES
gabarielleg
has source
Visio complète

Annotations

[Annotation #8610] 2022-01-18 15:42:44 Samuel Szoniecky tagging
Value Purpose
gabarielleg a taggé le document Generative adversarial nets avec le tag simulacre
classifying
Target selector Selector type
o:Item
[Annotation #8653] 2022-01-18 15:43:20 Samuel Szoniecky tagging
Value Purpose
gabarielleg a taggé le document Generative adversarial nets avec le tag hypertrucage
classifying
Target selector Selector type
o:Item
[Annotation #8812] 2022-01-18 15:45:09 Samuel Szoniecky tagging
Value Purpose
gabarielleg a taggé le document Generative adversarial nets avec le tag Intelligence Artificielle
classifying
Target selector Selector type
o:Item
[Annotation #8884] 2022-01-18 15:45:57 Samuel Szoniecky tagging
Value Purpose
gabarielleg a taggé le document Generative adversarial nets avec le tag Deep Fakes
classifying
Target selector Selector type
o:Item
[Annotation #9598] 2022-01-18 15:56:11 Samuel Szoniecky tagging
Value Purpose
gabarielleg a taggé le document Generative adversarial nets avec le tag gé
classifying
Target selector Selector type
o:Item
[Annotation #9602] 2022-01-18 15:56:15 Samuel Szoniecky tagging
Value Purpose
gabarielleg a taggé le document Generative adversarial nets avec le tag génératif
classifying
Target selector Selector type
o:Item
[Annotation #9611] 2022-01-18 15:56:21 Samuel Szoniecky tagging
Value Purpose
gabarielleg a taggé le document Generative adversarial nets avec le tag modèle
classifying
Target selector Selector type
o:Item