e-commerce companies such as Amazon, Alibaba and Flipkart process billions of
orders every year. However, these orders represent only a small fraction of all
plausible orders. Exploring the space of all plausible orders could help us
better understand the relationships between the vari
本文提出了一种新的 GAN 框架,名为进化生成对抗网络 (E-GAN),该框架使用不同的对抗训练目标作为突变操作,通过进化一群生成器来适应环境 (判别器) 以实现稳定的 GAN 训练和改进的生成能力,并利用评估机制来衡量生成样本的质量和多样性,从而始终保留最佳基因用于进一步的训练,从而提高了 GAN 的整体训练效果和生成性能。