Generative adversarial network based on chaotic time series
Generative adversarial network based on chaotic time series
复制标题
DOI：
10.1038/s41598-019-49397-2
复制
发表时间：
2019-05
影响因子：
4.6
通讯作者：
M. Naruse;Takashi Matsubara;N. Chauvet;Kazutaka Kanno;Tianyu Yang;A. Uchida
中科院分区：
文献类型：
--
作者：
M. Naruse;Takashi Matsubara;N. Chauvet;Kazutaka Kanno;Tianyu Yang;A. Uchida
生成性对抗网络(GAN)在人工构建自然图像和相关功能方面正变得越来越重要，其中称为生成器和鉴别器的两种类型的网络通过对抗性机制进化。利用深度卷积神经网络及其相关技术，已经生成了高分辨率和高真实感的场景、人脸等。GAN通常需要大量真实的训练数据集，以及大量的伪随机数。在这项研究中，我们利用半导体激光器实验产生的混沌时间序列作为GaN的潜在变量，从而将混沌的内在本质反映或转换为产生的输出数据。我们表明，描述生成图像相对于输入潜变量微小变化的稳健性的邻近度相似性得到了增强，而通用性总体上没有严重下降。此外，我们证明了替代混沌时间序列消除了最初观察到的与混沌序列中固有的负自相关相对应的生成图像的特征。我们还讨论了利用混沌时间序列从训练好的生成器中检索图像的效果。
Generative adversarial networks (GANs) are becoming increasingly important in the artificial construction of natural images and related functionalities, wherein two types of networks called generators and discriminators evolve through adversarial mechanisms. Using deep convolutional neural networks and related techniques, high-resolution and highly realistic scenes, human faces, etc. have been generated. GANs generally require large amounts of genuine training data sets, as well as vast amounts of pseudorandom numbers. In this study, we utilized chaotic time series generated experimentally by semiconductor lasers for the latent variables of a GAN, whereby the inherent nature of chaos could be reflected or transformed into the generated output data. We show that the similarity in proximity, which describes the robustness of the generated images with respect to minute changes in the input latent variables, is enhanced, while the versatility overall is not severely degraded. Furthermore, we demonstrate that the surrogate chaos time series eliminates the signature of the generated images that is originally observed corresponding to the negative autocorrelation inherent in the chaos sequence. We also address the effects of utilizing chaotic time series to retrieve images from the trained generator.