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 2301.04333cs.LGcs.AI
收藏

神经元控制微分方程的可学习路径

Learnable Path in Neural Controlled Differential Equations

Yonsei University(延世大学);Electronics and Telecommunications Research Institute (ETRI)(韩国电子通信研究院)

Sheo Yon Jhin, Minju Jo, Seungji Kook, Noseong Park, Sungpil Woo, Sunhwan Lim

摘要:

神经控制微分方程(NCDE)是递归神经网络(RNN)的连续类似物,是(不规则)时间序列处理的专用模型。与类似的模型相比,例如,神经常微分方程(NODE),NCDE的关键区别特征是i)采用由插值算法从每个原始离散时间序列样本创建的连续路径,以及ii)采用Riemann-Stieltjes积分。这是连续的路径,使NCDE类似于连续的RNN。然而,NCDE使用现有的插值算法来创建路径,这是不清楚的,他们是否可以创建一个最优的路径。为此,我们提出了一种方法来生成另一个潜在的路径(而不是依赖于现有的插值算法),这是相同的学习一个合适的插值方法。我们设计了一个基于NCDE和NODE的编解码器模块,并为它设计了一种特殊的训练方法,该方法在时间序列分类和预测方面都表现出了最好的性能。

英文摘要:

Neural controlled differential equations (NCDEs), which are continuous analogues to recurrent neural networks (RNNs), are a specialized model in (irregular) time-series processing. In comparison with similar models, e.g., neural ordinary differential equations (NODEs), the key distinctive characteristics of NCDEs are i) the adoption of the continuous path created by an interpolation algorithm from each raw discrete time-series sample and ii) the adoption of the Riemann--Stieltjes integral. It is the continuous path which makes NCDEs be analogues to continuous RNNs. However, NCDEs use existing interpolation algorithms to create the path, which is unclear whether they can create an optimal path. To this end, we present a method to generate another latent path (rather than relying on existing interpolation algorithms), which is identical to learning an appropriate interpolation method. We design an encoder-decoder module based on NCDEs and NODEs, and a special training method for it. Our method shows the best performance in both time-series classification and forecasting.

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。

↑