Generative Adversarial Networks
Contenu
- Titre
- Generative Adversarial Networks
- Date de soumission
- 24 mars 2023 à 08:58:41 +00:00
- Créateur
- Ian J. Goodfellow
- Jean Pouget-Abadie
- Mehdi Mirza
- Bing Xu
- David Warde-Farley
- Sherjil Ozair
- Aaron Courville
- Yoshua Bengio
- Est référencé par
- BIBJXMGZ
- Résumé
- 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.
- Date
- 10 juin 2014
- doi
- 10.48550/arXiv.1406.2661
- Source
- arXiv.org
- is compiled by
- Lucky Semiosis
- Complexité
-
693
- Date de modification
- 8 septembre 2023 à 06:54:19 +00:00
- Détails de la complexité
- Physique,1,,,,,49,49
- Physique,2,,,,,59,118
- Actant,2,,,,,9,18
- Concept,1,,,,,48,48
- Concept,2,,,,,60,120
- Rapport,1,1,Physique,Concept,properties,48,48
- Rapport,1,1,Physique,Physique,values,48,48
- Rapport,1,1,Physique,Actant,dcterms:creator,8,8
- Rapport,2,2,Actant,Concept,properties,44,88
- Rapport,2,2,Actant,Physique,values,44,88
- Rapport,1,1,Physique,Actant,cito:isCompiledBy,1,1
- Rapport,1,1,Physique,Concept,skos:semanticRelation,3,3
- Rapport,2,2,Concept,Concept,properties,9,18
- Rapport,2,2,Concept,Physique,values,9,18
- Rapport,1,1,Physique,Physique,media,2,2
- Rapport,2,2,Physique,Concept,properties,4,8
- Rapport,2,2,Physique,Physique,values,4,8
- Rapport,1,1,Physique,Physique,uri,2,2
- Totaux de la complexité
- Physique,2,1,2,108,167
- Actant,1,2,2,9,18
- Concept,2,1,2,108,168
- Rapport,13,1,2,226,340
- Existence,18,1,2,451,693
-
568
- Date de modification
- 8 janvier 2024 à 10:57:46 +00:00
- Détails de la complexité
- dimension,niv (sujet),niv objet,sujet,objet,prédicat,nb,c
- Physique,1,,,,,22,22
- Physique,2,,,,,63,126
- Actant,1,,,,,1,1
- Actant,2,,,,,9,18
- Concept,1,,,,,11,11
- Concept,2,,,,,58,116
- Rapport,1,1,Actant,Concept,properties,11,11
- Rapport,1,1,Actant,Physique,values,21,21
- Rapport,1,1,Actant,Physique,owner,1,1
- Rapport,2,1,Actant,Physique,oa:hasSource,3,6
- Rapport,2,2,Actant,Concept,properties,55,110
- Rapport,2,2,Actant,Physique,values,55,110
- Rapport,1,1,Actant,Actant,dcterms:creator,8,8
- Rapport,1,1,Actant,Actant,cito:isCompiledBy,1,1
- Rapport,1,1,Actant,Concept,skos:semanticRelation,3,3
- Rapport,1,1,Actant,Physique,media,2,2
- Rapport,1,1,Actant,Physique,uri,1,1
- Totaux de la complexité
- Physique,2,1,2,85,148
- Actant,2,1,2,10,19
- Concept,2,1,2,69,127
- Rapport,11,1,2,161,274
- Existence,17,1,2,325,568,
- Collections
- Zotero
Annotations
| Valeur | Purpose |
|---|---|
|
Zotero automatique tagger a taggé le document Generative Adversarial Networks avec le tag computer science
|
classifying |
| Target selector | Selector type |
|---|---|
| o:Item |
| Valeur | Purpose |
|---|---|
|
Zotero automatique tagger a taggé le document Generative Adversarial Networks avec le tag Machine Learning
|
classifying |
| Target selector | Selector type |
|---|---|
| o:Item |
| Valeur | Purpose |
|---|---|
|
Zotero automatique tagger a taggé le document Generative Adversarial Networks avec le tag Statistics
|
classifying |
| Target selector | Selector type |
|---|---|
| o:Item |