arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.06115cs.LGcs.CVhep-ph
收藏

对称性符合AI

Symmetry meets AI

Universitat de València(瓦伦西亚大学);CSIC(西班牙国家研究委员会);University of Sussex(萨塞克斯大学)

Gabriela Barenboim, Johannes Hirn, Veronica Sanz

摘要:

我们探讨神经网络(NN)是否可以{ \it discover}对称性的存在,因为它们学习执行任务。为此,我们训练数百个NN在{ \it诱饵任务}上基于良好控制的物理模板,其中没有提供关于对称性的信息。我们使用所有这些NN的最后一个隐藏层的输出,投影到更少的维度,作为对称性分类任务的输入,并表明原始NN确实在没有指导的情况下识别了对称性信息。作为这一过程的跨学科应用,我们确定了对称性的存在和水平,从不同风格的艺术绘画,如毕加索,波洛克和梵高。

英文摘要:

We explore whether Neural Networks (NNs) can {\it discover} the presence of symmetries as they learn to perform a task. For this, we train hundreds of NNs on a {\it decoy task} based on well-controlled Physics templates, where no information on symmetry is provided. We use the output from the last hidden layer of all these NNs, projected to fewer dimensions, as the input for a symmetry classification task, and show that information on symmetry had indeed been identified by the original NN without guidance. As an interdisciplinary application of this procedure, we identify the presence and level of symmetry in artistic paintings from different styles such as those of Picasso, Pollock and Van Gogh.

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。

↑