arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2010.06178cs.LG
收藏

差分径向基函数网络在层序建模中的应用

Differential radial basis function network for sequence modelling

Loblaw Companies Limited(罗布劳公司有限公司);Coventry University(考文垂大学)

Kojo Sarfo Gyamfi, James Brusey, Elena Gaura

摘要:

我们提出了一个差分径向基函数(RBF)网络称为RBF-DiffNet -其隐藏层块是偏微分方程(PDE)线性的RBF -使基线RBF网络的鲁棒性在连续的数据中的噪声。假设序列数据来源于对潜在PDE的解的离散化,差分RBF网络学习PDE的常数线性系数,从而通过以下修改的后向欧拉更新来正则化RBF网络。我们的实验验证了差分RBF网络上的Logistic映射混沌时间序列,以及30个现实世界的时间序列沃尔玛提供的M5预测比赛。该模型与归一化和非归一化RBF网络,ARIMA,多层感知器(MLP)和具有长短期记忆(LSTM)块的递归网络的集成进行了比较。从实验结果来看,RBF-DiffNet在预测误差方面始终显示出比基线RBF网络显著的降低(例如,M5数据集上的均方根缩放误差减少了26%); RBF-DiffNet还显示出与LSTM集成相当的性能,其计算时间不到LSTM的十六分之一。因此,我们提出的网络能够在存在观测噪声的情况下进行更准确的预测,例如利用RBF网络的模型可解释性,快速训练和函数逼近特性的时间序列预测。

英文摘要:

We propose a differential radial basis function (RBF) network termed RBF-DiffNet -- whose hidden layer blocks are partial differential equations (PDEs) linear in terms of the RBF -- to make the baseline RBF network robust to noise in sequential data. Assuming that the sequential data derives from the discretisation of the solution to an underlying PDE, the differential RBF network learns constant linear coefficients of the PDE, consequently regularising the RBF network by following modified backward-Euler updates. We experimentally validate the differential RBF network on the logistic map chaotic timeseries as well as on 30 real-world timeseries provided by Walmart in the M5 forecasting competition. The proposed model is compared with the normalised and unnormalised RBF networks, ARIMA, and ensembles of multilayer perceptrons (MLPs) and recurrent networks with long short-term memory (LSTM) blocks. From the experimental results, RBF-DiffNet consistently shows a marked reduction over the baseline RBF network in terms of the prediction error (e.g., 26% reduction in the root mean squared scaled error on the M5 dataset); RBF-DiffNet also shows a comparable performance to the LSTM ensemble at less than one-sixteenth the LSTM computational time. Our proposed network consequently enables more accurate predictions -- in the presence of observational noise -- in sequence modelling tasks such as timeseries forecasting that leverage the model interpretability, fast training, and function approximation properties of the RBF network.

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。

↑