arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1910.02409cs.LGcs.AI
收藏

寻找(不)稳定的平衡:在没有数据的情况下训练生成模型的实验

Searching for an (un)stable equilibrium: experiments in training generative models without data

Goldsmiths, University of London(伦敦大学金史密斯学院);University of the Arts London(伦敦艺术大学)

Terence Broad, Mick Grierson

摘要:

本文详细介绍了围绕一个正在进行的系列作品称为(不)稳定的平衡发展的艺术实践。这些作品是使用现代机器工具包来训练生成模型而无需数据的产物,这种方法类似于传统的生成艺术,其中直观地探索动态系统的潜在生成可能性。我们讨论了一些已在实验过程中学到的指导原则,目前的第一系列作品的实施细节,并讨论未来实验的可能性。

英文摘要:

This paper details a developing artistic practice around an ongoing series of works called (un)stable equilibrium. These works are the product of using modern machine toolkits to train generative models without data, an approach akin to traditional generative art where dynamical systems are explored intuitively for their latent generative possibilities. We discuss some of the guiding principles that have been learnt in the process of experimentation, present details of the implementation of the first series of works and discuss possibilities for future experimentation.

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。

↑