arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2110.03393cs.LG
收藏

基于深度学习构造的预测区间的多变量异常检测

Multivariate Anomaly Detection based on Prediction Intervals Constructed using Deep Learning

University of the Witwatersrand(金山大学);University of Johannesburg(约翰内斯堡大学)

Thabang Mathonsi, Terence L. van Zyl

摘要:

事实证明,在某些情况下,深度学习模型在预测方面可以优于传统的统计方法。此外,已经开发了用于量化预测不确定性(预测区间)的各种技术。在本文中,我们利用人工神经网络的帮助下构建的预测区间检测异常的多元设置。现有的基于深度学习的异常检测方法的挑战包括$(i)$可能是计算密集型的参数的大集合,$(ii)$返回太多的假阳性,使得该技术不实用,$(iii)$需要标记的数据集用于训练,这在现实生活中通常不普遍。我们的方法克服了这些挑战。我们将我们的方法与通常首选的成熟统计模型进行基准测试。我们重点研究了三种深度学习架构,即级联神经网络、水库计算和长短期记忆递归神经网络。我们的发现是深度学习优于后者(或者至少是竞争对手)。

英文摘要:

It has been shown that deep learning models can under certain circumstances outperform traditional statistical methods at forecasting. Furthermore, various techniques have been developed for quantifying the forecast uncertainty (prediction intervals). In this paper, we utilize prediction intervals constructed with the aid of artificial neural networks to detect anomalies in the multivariate setting. Challenges with existing deep learning-based anomaly detection approaches include $(i)$ large sets of parameters that may be computationally intensive to tune, $(ii)$ returning too many false positives rendering the techniques impractical for use, $(iii)$ requiring labeled datasets for training which are often not prevalent in real life. Our approach overcomes these challenges. We benchmark our approach against the oft-preferred well-established statistical models. We focus on three deep learning architectures, namely, cascaded neural networks, reservoir computing and long short-term memory recurrent neural networks. Our finding is deep learning outperforms (or at the very least is competitive to) the latter.

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。

↑