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 2310.14720cs.LGstat.ML
收藏

扩展深度自适应输入归一化:用于神经网络时间序列数据预处理

Extended Deep Adaptive Input Normalization for Preprocessing Time Series Data for Neural Networks

Imperial College London(伦敦帝国学院);American Express(美国运通公司)

Marcus A. K. September, Francesco Sanna Passino, Leonie Goldmann, Anton Hinel

AI总结:

提出EDAIN自适应归一化层,端到端学习时间序列数据的归一化方式,在合成数据、信用违约和限价订单簿数据集上优于传统方法。

摘要:

数据预处理是任何机器学习流程中的关键部分,它对性能和训练效率都有显著影响。当使用深度神经网络进行时间序列预测和分类时,这一点尤为明显:真实世界的时间序列数据往往表现出多模态、偏斜和异常值等不规则性,如果这些特征未得到充分处理,模型性能会迅速下降。在这项工作中,我们提出了EDAIN(扩展深度自适应输入归一化)层,这是一种新颖的自适应神经层,它以端到端的方式学习如何针对给定任务适当地归一化不规则的时间序列数据,而不是使用固定的归一化方案。这是通过使用反向传播同时优化其未知参数与深度神经网络来实现的。我们的实验使用了合成数据、信用违约预测数据集和大规模限价订单簿基准数据集,结果表明,与传统归一化方法和现有的自适应时间序列预处理层相比,EDAIN层具有更优越的性能。

英文摘要:

Data preprocessing is a crucial part of any machine learning pipeline, and it can have a significant impact on both performance and training efficiency. This is especially evident when using deep neural networks for time series prediction and classification: real-world time series data often exhibit irregularities such as multi-modality, skewness and outliers, and the model performance can degrade rapidly if these characteristics are not adequately addressed. In this work, we propose the EDAIN (Extended Deep Adaptive Input Normalization) layer, a novel adaptive neural layer that learns how to appropriately normalize irregular time series data for a given task in an end-to-end fashion, instead of using a fixed normalization scheme. This is achieved by optimizing its unknown parameters simultaneously with the deep neural network using back-propagation. Our experiments, conducted using synthetic data, a credit default prediction dataset, and a large-scale limit order book benchmark dataset, demonstrate the superior performance of the EDAIN layer when compared to conventional normalization methods and existing adaptive time series preprocessing layers.

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。

↑