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 2011.01243astro-ph.IMastro-ph.SRcs.LGphysics.data-an
收藏

周期变星的循环排列不变神经网络分类

Classification of Periodic Variable Stars with Novel Cyclic-Permutation Invariant Neural Networks

University of California, Berkeley(加州大学伯克利分校);Lawrence Berkeley National Laboratory(劳伦斯伯克利国家实验室)

Keming Zhang, Joshua S. Bloom

摘要:

神经网络(NN)已被证明是有竞争力的国家的最先进的特征工程和随机森林(RF)分类的周期性变星。虽然以前的工作利用神经网络利用周期折叠多个周期的时间序列到一个单一的周期-从时间-空间相空间-没有办法到目前为止已经利用的事实,网络预测应该是不变的周期折叠序列的初始阶段。初始阶段对于可变性的物理起源是外生的,因此应该被排除在外。在这里,我们提出了循环置换不变网络,这是一类新的NN,通过极坐标卷积保证了对相移的不变性,我们通过“对称填充”实现。“在三个不同的变星光变曲线数据集上,我们证明了循环排列不变网络的两种实现:iTCN和iResNet,始终优于非不变基线,并将总体错误率降低了4%至22%。在10类OGLE-III样本中,iTCN/iResNet实现了93.4%/93.3%的平均每类准确率,而在最近的一项研究中,使用相同的数据,RNN/RF的准确率为70.5%/89.5%。在非天文学基准上找到改进,我们建议这里介绍的方法也应该适用于广泛的科学领域,由于物理对称性,周期性数据丰富。

英文摘要:

Neural networks (NNs) have been shown to be competitive against state-of-the-art feature engineering and random forest (RF) classification of periodic variable stars. Although previous work utilising NNs has made use of periodicity by period folding multiple-cycle time-series into a single cycle -- from time-space to phase-space -- no approach to date has taken advantage of the fact that network predictions should be invariant to the initial phase of the period-folded sequence. Initial phase is exogenous to the physical origin of the variability and should thus be factored out. Here, we present cyclic-permutation invariant networks, a novel class of NNs for which invariance to phase shifts is guaranteed through polar coordinate convolutions, which we implement by means of "Symmetry Padding." Across three different datasets of variable star light curves, we show that two implementations of the cyclic-permutation invariant network: the iTCN and the iResNet, consistently outperform non-invariant baselines and reduce overall error rates by between 4% to 22%. Over a 10-class OGLE-III sample, the iTCN/iResNet achieves an average per-class accuracy of 93.4%/93.3%, compared to RNN/RF accuracies of 70.5%/89.5% in a recent study using the same data. Finding improvement on a non-astronomy benchmark, we suggest that the methodology introduced here should also be applicable to a wide range of science domains where periodic data abounds due to physical symmetries.

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。

↑