论文标题
具有生成模型的创造性发散综合
Creative divergent synthesis with generative models
论文作者
论文摘要
现在，机器学习方法可以在诸如图像，音频或视频之类的众多域中获得令人印象深刻的发电能力。但是，大多数培训\和评估框架都围绕严格建模原始数据分布而不是试图推断出它的想法。这排除了此类模型与原始分布不同的能力，因此表现出一些创造性的特征。在本文中，我们提出了有关如何实现这一复杂目标的各种观点，并在我们的新颖培训目标中提供了初步结果，称为\ textit {有界的对抗性脱落}（不良）。
Machine learning approaches now achieve impressive generation capabilities in numerous domains such as image, audio or video. However, most training \& evaluation frameworks revolve around the idea of strictly modelling the original data distribution rather than trying to extrapolate from it. This precludes the ability of such models to diverge from the original distribution and, hence, exhibit some creative traits. In this paper, we propose various perspectives on how this complicated goal could ever be achieved, and provide preliminary results on our novel training objective called \textit{Bounded Adversarial Divergence} (BAD).
