arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.01075cs.CGcs.DScs.LG
收藏

一个NN模型能简单地学习平面布局吗?

Can an NN model plainly learn planar layouts?

Utrecht University(乌得勒支大学)

Smon van Wageningen, Tamara Mchedlidze

摘要:

平面图形绘图往往是美观的。在这张海报中,我们探索了神经网络学习各种平面图类的能力。此外,我们还研究了该模型在推广平面性之外的有效性。我们发现,该模型可以优于传统的技术,某些图形类。然而,该模型似乎更容易受到数据随机性的影响,并且似乎不如预期的那么稳健。

英文摘要:

Planar graph drawings tend to be aesthetically pleasing. In this poster we explore a Neural Network's capability of learning various planar graph classes. Additionally, we also investigate the effectiveness of the model in generalizing beyond planarity. We find that the model can outperform conventional techniques for certain graph classes. The model, however, appears to be more susceptible to randomness in the data, and seems to be less robust than expected.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑