We propose a framework for generating samples from a probability distribution that differs from the probability distribution of the training set. We use an adversarial process that simultaneously trains three networks, a generator and two discriminators. We refer to this new model as regularized generative adversarial network (RegGAN). We evaluate RegGAN on a synthetic dataset composed of gray scale images and we further show that it can be used to learn some pre-specified notions in topology (basic topology properties). The work is motivated by practical problems encountered while using generative methods in the art world.

翻译：我们提议了一个框架,用于从与培训组合的概率分布不同的概率分布中生成样本;我们采用对抗性程序,同时培训三个网络、一个发电机和两个歧视者;我们把这一新模式称为正规化的基因对抗网络(RegGAN);我们用灰度图像组成的合成数据集对RegGAN进行评估,我们进一步表明,它可以用来学习一些在地形学(基本地形特性)方面预先确定的概念;这项工作的动机是,在艺术界使用基因化方法时遇到实际问题。