arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2204.05192cs.LGcs.NE
收藏

任务同步循环神经网络

Task-Synchronized Recurrent Neural Networks

Kaunas University of Technology(考纳斯理工大学)

Mantas Lukoševičius, Arnas Uselis

AI总结:

针对不规则时间采样数据,本文提出通过在时间上重采样 RNN 以匹配任务时间的 TSESN 与 TSGRU,无需额外训练或计算,并在多个真实数据集上验证其优势。

摘要:

数据在时间上往往是不规则采样的。传统上,使用循环神经网络(RNN)处理这一问题时,会忽略这一事实、将时间差作为额外输入,或对数据进行重采样。所有这些方法都有其缺点。我们提出了一种优雅而直接的替代方法:实际上是在时间上对 RNN 进行重采样,以匹配数据或当前任务的时间。我们使用回声状态网络(Echo State Network,ESN)和门控循环单元(Gated Recurrent Unit,GRU)作为解决方案的基础。这类 RNN 可被视为连续时间动力系统的离散化,这为我们的方法提供了坚实的理论基础。我们的任务同步 ESN(Task-Synchronized ESN,TSESN)和 GRU(TSGRU)模型允许直接设置模型时间,并且与其常规对应模型相比,不需要额外的训练、参数调整或计算(求解微分方程或插值数据),从而保持了原有效率。我们通过实验证实,我们的模型能够有效补偿数据的时间非均匀性,并证明在若干真实世界的非均匀时间数据集上,它们相较于数据重采样、经典 RNN 方法以及为处理时间不规则性而提出的其他 RNN 模型表现更优。我们在 https://github.com/oshapio/task-synchronized-RNNs 上开源了代码。

英文摘要:

Data are often sampled irregularly in time. Dealing with this using Recurrent Neural Networks (RNNs) traditionally involved ignoring the fact, feeding the time differences as additional inputs, or resampling the data. All these methods have their shortcomings. We propose an elegant straightforward alternative approach where instead the RNN is in effect resampled in time to match the time of the data or the task at hand. We use Echo State Network (ESN) and Gated Recurrent Unit (GRU) as the basis for our solution. Such RNNs can be seen as discretizations of continuous-time dynamical systems, which gives a solid theoretical ground to our approach. Our Task-Synchronized ESN (TSESN) and GRU (TSGRU) models allow for a direct model time setting and require no additional training, parameter tuning, or computation (solving differential equations or interpolating data) compared to their regular counterparts, thus retaining their original efficiency. We confirm empirically that our models can effectively compensate for the time-non-uniformity of the data and demonstrate that they compare favorably to data resampling, classical RNN methods, and alternative RNN models proposed to deal with time irregularities on several real-world nonuniform-time datasets. We open-source the code at https://github.com/oshapio/task-synchronized-RNNs .

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。

↑