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 1703.07015cs.LG
收藏

用深度神经网络建模长期和短期时间模式

Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks

Carnegie Mellon University(卡内基梅隆大学)

Guokun Lai, Wei-Cheng Chang, Yiming Yang, Hanxiao Liu

摘要:

多变量时间序列预测是一个重要的机器学习问题,涉及许多领域,包括预测太阳能发电厂的能量输出、电力消耗和交通拥堵情况。在这些实际应用中出现的时态数据往往涉及长期和短期模式的混合,传统的方法,如自回归模型和高斯过程可能会失败。在本文中,我们提出了一种新的深度学习框架,即长期和短期时间序列网络(LSTNet),以解决这一开放性挑战。LSTNet使用卷积神经网络(CNN)和递归神经网络(RNN)来提取变量之间的短期局部依赖模式,并发现时间序列趋势的长期模式。此外,我们利用传统的自回归模型来解决神经网络模型的尺度不敏感问题。在我们对具有复杂重复模式混合的真实数据的评估中,LSTNet比几种最先进的基线方法实现了显着的性能改进。所有的数据和实验代码都可以在线获得。

英文摘要:

Multivariate time series forecasting is an important machine learning problem across many domains, including predictions of solar plant energy output, electricity consumption, and traffic jam situation. Temporal data arise in these real-world applications often involves a mixture of long-term and short-term patterns, for which traditional approaches such as Autoregressive models and Gaussian Process may fail. In this paper, we proposed a novel deep learning framework, namely Long- and Short-term Time-series network (LSTNet), to address this open challenge. LSTNet uses the Convolution Neural Network (CNN) and the Recurrent Neural Network (RNN) to extract short-term local dependency patterns among variables and to discover long-term patterns for time series trends. Furthermore, we leverage traditional autoregressive model to tackle the scale insensitive problem of the neural network model. In our evaluation on real-world data with complex mixtures of repetitive patterns, LSTNet achieved significant performance improvements over that of several state-of-the-art baseline methods. All the data and experiment codes are available online.

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。

↑