首页 | 本学科首页   官方微博 | 高级检索  
     

生成式对抗网络GAN的研究进展与展望
引用本文:王坤峰,苟超,段艳杰,林懿伦,郑心湖,王飞跃.生成式对抗网络GAN的研究进展与展望[J].自动化学报,2017,43(3):321-332.
作者姓名:王坤峰  苟超  段艳杰  林懿伦  郑心湖  王飞跃
作者单位:1.中国科学院自动化研究所复杂系统管理与控制国家重点实验室 北京 100190 中国
基金项目:国家自然科学基金(61533019,71232006,91520301)资助
摘    要:生成式对抗网络GAN(Generative adversarial networks)目前已经成为人工智能学界一个热门的研究方向.GAN的基本思想源自博弈论的二人零和博弈,由一个生成器和一个判别器构成,通过对抗学习的方式来训练.目的是估测数据样本的潜在分布并生成新的数据样本.在图像和视觉计算、语音和语言处理、信息安全、棋类比赛等领域,GAN正在被广泛研究,具有巨大的应用前景.本文概括了GAN的研究进展,并进行展望.在总结了GAN的背景、理论与实现模型、应用领域、优缺点及发展趋势之后,本文还讨论了GAN与平行智能的关系,认为GAN可以深化平行系统的虚实互动、交互一体的理念,特别是计算实验的思想,为ACP(Artificial societies,computational experiments,and parallel execution)理论提供了十分具体和丰富的算法支持.

关 键 词:生成式对抗网络    生成式模型    零和博弈    对抗学习    平行智能    ACP方法
收稿时间:2017-02-01

Generative Adversarial Networks: The State of the Art and Beyond
WANG Kun-Feng,GOU Chao,DUAN Yan-Jie,LIN Yi-Lun,ZHENG Xin-Hu,WANG Fei-Yue.Generative Adversarial Networks: The State of the Art and Beyond[J].Acta Automatica Sinica,2017,43(3):321-332.
Authors:WANG Kun-Feng  GOU Chao  DUAN Yan-Jie  LIN Yi-Lun  ZHENG Xin-Hu  WANG Fei-Yue
Abstract:Generative adversarial networks (GANs) have become a hot research topic in artificial intelligence. Inspired by the two-player zero-sum game, GAN is composed of a generator and a discriminator, both trained with the adversarial learning mechanism. The aim of GAN is to estimate the potential distribution of existing data and generate new data samples from the same distribution. Since its initiation, GAN has been widely studied due to its enormous prospect for applications, including image and vision computing, speech and language processing, information security, and chess game. In this paper we summarize the state of the art of GAN and look into its future. First of all, we survey the GAN's background, theoretic and implementation models, application fields, advantages and disadvantages, and development trends. Then, we investigate the relation between GAN and parallel intelligence with the conclusion that GAN has a great potential in parallel systems especially in computational experiments, in terms of virtual-real interaction and integration. Finally, we clarify that GAN can provide specific and substantial algorithmic support for the ACP theory.
Keywords:Generative adversarial networks  generative models  zero-sum game  adversarial learning  parallel intelligence  ACP methodology
点击此处可从《自动化学报》浏览原始摘要信息
点击此处可从《自动化学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号