论文标题
关于生成对抗网络的综述：算法，理论和应用
A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
论文作者
论文摘要
生成对抗网络（GAN）最近是一个热门研究主题。自2014年以来，已经对甘斯进行了广泛的研究，并提出了大量算法。但是，很少有全面的研究解释不同剂量变体之间的联系，以及它们的发展方式。在本文中，我们尝试从算法，理论和应用的角度对各种gan方法进行综述。首先，详细介绍了大多数GAN算法的动机，数学表示和结构。此外，GAN已与其他机器学习算法结合使用，用于特定应用，例如半监督学习，转移学习和强化学习。本文比较了这些gan方法的共同点和差异。其次，研究了与gan有关的理论问题。第三，说明了gan在图像处理和计算机视觉，自然语言处理，音乐，语音和音频，医学领域和数据科学中的典型应用。最后，指出了未来针对GAN的开放研究问题。
Generative adversarial networks (GANs) are a hot research topic recently. GANs have been widely studied since 2014, and a large number of algorithms have been proposed. However, there is few comprehensive study explaining the connections among different GANs variants, and how they have evolved. In this paper, we attempt to provide a review on various GANs methods from the perspectives of algorithms, theory, and applications. Firstly, the motivations, mathematical representations, and structure of most GANs algorithms are introduced in details. Furthermore, GANs have been combined with other machine learning algorithms for specific applications, such as semi-supervised learning, transfer learning, and reinforcement learning. This paper compares the commonalities and differences of these GANs methods. Secondly, theoretical issues related to GANs are investigated. Thirdly, typical applications of GANs in image processing and computer vision, natural language processing, music, speech and audio, medical field, and data science are illustrated. Finally, the future open research problems for GANs are pointed out.
