Generative Adversarial Networks

被引：14793

作者：

Goodfellow, Ian ^{[1
]}

Pouget-Abadie, Jean ^{[2
]}

Mirza, Mehdi ^{[2
]}

Xu, Bing ^{[2
]}

Warde-Farley, David ^{[2
]}

Ozair, Sherjil ^{[2
]}

Courville, Aaron ^{[2
]}

Bengio, Yoshua ^{[2
]}

机构：

[1] Google Brain, Mountain View, CA 94043 USA

[2] Univ Montreal, Montreal, PQ, Canada

来源：

COMMUNICATIONS OF THE ACM | 2020年 / 63卷 / 11期

关键词：

Deep learning - Probability distributions - Game theory;

D O I：

10.1145/3422622

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

Generative adversarial networks are a kind of artificial intelligence algorithm designed to solve the generative modeling problem. The goal of a generative model is to study a collection of training examples and learn the probability distribution that generated them. Generative Adversarial Networks (GANs) are then able to generate more examples from the estimated probability distribution. Generative models based on deep learning are common, but GANs are among the most successful generative models (especially in terms of their ability to generate realistic high-resolution images). GANs have been successfully applied to a wide variety of tasks (mostly in research settings) but continue to present unique challenges and research opportunities because they are based on game theory while most other approaches to generative modeling are based on optimization.

引用

页码：139 / 144

页数：6