论文标题
通过学习交流而没有人类数据的没有人类数据的新颖的字形
Generating Novel Glyph without Human Data by Learning to Communicate
论文作者
论文摘要
在本文中，我们提出了神经字形，该系统是一种在没有任何训练数据的情况下生成新颖的字形的系统。生成器和分类器经过训练，可以通过视觉符号作为介质进行通信，从而强制发电机提出一组独特的符号。我们的方法会导致类似于人为字形的字形，这可能意味着现有字形的视觉外观可以归因于通过写作的限制。描述了启用此框架并提供代码的重要技巧。
In this paper, we present Neural Glyph, a system that generates novel glyph without any training data. The generator and the classifier are trained to communicate via visual symbols as a medium, which enforces the generator to come up with a set of distinctive symbols. Our method results in glyphs that resemble the human-made glyphs, which may imply that the visual appearances of existing glyphs can be attributed to constraints of communication via writing. Important tricks that enable this framework are described and the code is made available.
